Kernel/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2024-12-29 09:13:38 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Networking changes for 5.13.

Browse Source 
Core:
 
  - bpf:
 	- allow bpf programs calling kernel functions (initially to
 	  reuse TCP congestion control implementations)
 	- enable task local storage for tracing programs - remove the
 	  need to store per-task state in hash maps, and allow tracing
 	  programs access to task local storage previously added for
 	  BPF_LSM
 	- add bpf_for_each_map_elem() helper, allowing programs to
 	  walk all map elements in a more robust and easier to verify
 	  fashion
 	- sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
 	  redirection
 	- lpm: add support for batched ops in LPM trie
 	- add BTF_KIND_FLOAT support - mostly to allow use of BTF
 	  on s390 which has floats in its headers files
 	- improve BPF syscall documentation and extend the use of kdoc
 	  parsing scripts we already employ for bpf-helpers
 	- libbpf, bpftool: support static linking of BPF ELF files
 	- improve support for encapsulation of L2 packets
 
  - xdp: restructure redirect actions to avoid a runtime lookup,
 	improving performance by 4-8% in microbenchmarks
 
  - xsk: build skb by page (aka generic zerocopy xmit) - improve
 	performance of software AF_XDP path by 33% for devices
 	which don't need headers in the linear skb part (e.g. virtio)
 
  - nexthop: resilient next-hop groups - improve path stability
 	on next-hops group changes (incl. offload for mlxsw)
 
  - ipv6: segment routing: add support for IPv4 decapsulation
 
  - icmp: add support for RFC 8335 extended PROBE messages
 
  - inet: use bigger hash table for IP ID generation
 
  - tcp: deal better with delayed TX completions - make sure we don't
 	give up on fast TCP retransmissions only because driver is
 	slow in reporting that it completed transmitting the original
 
  - tcp: reorder tcp_congestion_ops for better cache locality
 
  - mptcp:
 	- add sockopt support for common TCP options
 	- add support for common TCP msg flags
 	- include multiple address ids in RM_ADDR
 	- add reset option support for resetting one subflow
 
  - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
 	co-existence with UDP tunnel GRO, allowing the first to take
 	place correctly	even for encapsulated UDP traffic
 
  - micro-optimize dev_gro_receive() and flow dissection, avoid
 	retpoline overhead on VLAN and TEB GRO
 
  - use less memory for sysctls, add a new sysctl type, to allow using
 	u8 instead of "int" and "long" and shrink networking sysctls
 
  - veth: allow GRO without XDP - this allows aggregating UDP
 	packets before handing them off to routing, bridge, OvS, etc.
 
  - allow specifing ifindex when device is moved to another namespace
 
  - netfilter:
 	- nft_socket: add support for cgroupsv2
 	- nftables: add catch-all set element - special element used
 	  to define a default action in case normal lookup missed
 	- use net_generic infra in many modules to avoid allocating
 	  per-ns memory unnecessarily
 
  - xps: improve the xps handling to avoid potential out-of-bound
 	accesses and use-after-free when XPS change race with other
 	re-configuration under traffic
 
  - add a config knob to turn off per-cpu netdev refcnt to catch
 	underflows in testing
 
 Device APIs:
 
  - add WWAN subsystem to organize the WWAN interfaces better and
    hopefully start driving towards more unified and vendor-
    -independent APIs
 
  - ethtool:
 	- add interface for reading IEEE MIB stats (incl. mlx5 and
 	  bnxt support)
 	- allow network drivers to dump arbitrary SFP EEPROM data,
 	  current offset+length API was a poor fit for modern SFP
 	  which define EEPROM in terms of pages (incl. mlx5 support)
 
  - act_police, flow_offload: add support for packet-per-second
 	policing (incl. offload for nfp)
 
  - psample: add additional metadata attributes like transit delay
 	for packets sampled from switch HW (and corresponding egress
 	and policy-based sampling in the mlxsw driver)
 
  - dsa: improve support for sandwiched LAGs with bridge and DSA
 
  - netfilter:
 	- flowtable: use direct xmit in topologies with IP
 	  forwarding, bridging, vlans etc.
 	- nftables: counter hardware offload support
 
  - Bluetooth:
 	- improvements for firmware download w/ Intel devices
 	- add support for reading AOSP vendor capabilities
 	- add support for virtio transport driver
 
  - mac80211:
 	- allow concurrent monitor iface and ethernet rx decap
 	- set priority and queue mapping for injected frames
 
  - phy: add support for Clause-45 PHY Loopback
 
  - pci/iov: add sysfs MSI-X vector assignment interface
 	to distribute MSI-X resources to VFs (incl. mlx5 support)
 
 New hardware/drivers:
 
  - dsa: mv88e6xxx: add support for Marvell mv88e6393x -
 	11-port Ethernet switch with 8x 1-Gigabit Ethernet
 	and 3x 10-Gigabit interfaces.
 
  - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365
 	and BCM63xx switches
 
  - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches
 
  - ath11k: support for QCN9074 a 802.11ax device
 
  - Bluetooth: Broadcom BCM4330 and BMC4334
 
  - phy: Marvell 88X2222 transceiver support
 
  - mdio: add BCM6368 MDIO mux bus controller
 
  - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips
 
  - mana: driver for Microsoft Azure Network Adapter (MANA)
 
  - Actions Semi Owl Ethernet MAC
 
  - can: driver for ETAS ES58X CAN/USB interfaces
 
 Pure driver changes:
 
  - add XDP support to: enetc, igc, stmmac
  - add AF_XDP support to: stmmac
 
  - virtio:
 	- page_to_skb() use build_skb when there's sufficient tailroom
 	  (21% improvement for 1000B UDP frames)
 	- support XDP even without dedicated Tx queues - share the Tx
 	  queues with the stack when necessary
 
  - mlx5:
 	- flow rules: add support for mirroring with conntrack,
 	  matching on ICMP, GTP, flex filters and more
 	- support packet sampling with flow offloads
 	- persist uplink representor netdev across eswitch mode
 	  changes
 	- allow coexistence of CQE compression and HW time-stamping
 	- add ethtool extended link error state reporting
 
  - ice, iavf: support flow filters, UDP Segmentation Offload
 
  - dpaa2-switch:
 	- move the driver out of staging
 	- add spanning tree (STP) support
 	- add rx copybreak support
 	- add tc flower hardware offload on ingress traffic
 
  - ionic:
 	- implement Rx page reuse
 	- support HW PTP time-stamping
 
  - octeon: support TC hardware offloads - flower matching on ingress
 	and egress ratelimitting.
 
  - stmmac:
 	- add RX frame steering based on VLAN priority in tc flower
 	- support frame preemption (FPE)
 	- intel: add cross time-stamping freq difference adjustment
 
  - ocelot:
 	- support forwarding of MRP frames in HW
 	- support multiple bridges
 	- support PTP Sync one-step timestamping
 
  - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
 	learning, flooding etc.
 
  - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
 	SC7280 SoCs)
 
  - mt7601u: enable TDLS support
 
  - mt76:
 	- add support for 802.3 rx frames (mt7915/mt7615)
 	- mt7915 flash pre-calibration support
 	- mt7921/mt7663 runtime power management fixes
 
 Signed-off-by: Jakub Kicinski <kuba@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE6jPA+I1ugmIBA4hXMUZtbf5SIrsFAmCKFPIACgkQMUZtbf5S
 Irtw0g/+NA8bWdHNgG4H5rya0pv2z3IieLRmSdDfKRQQXcJpklawc5MKVVaTee/Q
 5/QqgPdCsu1LAU6JXBKsKmyDDaMlQKdWuKbOqDSiAQKoMesZStTEHf9d851ZzgxA
 Cdb6O7BD3lBl/IN+oxNG+KcmD1LKquTPKGySq2mQtEdLO12ekAsranzmj4voKffd
 q9tBShpXQ7Dq77DLYfiQXVCvsizNcbbJFuxX0o9Lpb9+61ZyYAbogZSa9ypiZZwR
 I/9azRBtJg7UV1aD/cLuAfy66Qh7t63+rCxVazs5Os8jVO26P/jQdisnnOe/x+p9
 wYEmKm3GSu0V4SAPxkWW+ooKusflCeqDoMIuooKt6kbP6BRj540veGw3Ww/m5YFr
 7pLQkTSP/tSjuGQIdBE1LOP5LBO8DZeC8Kiop9V0fzAW9hFSZbEq25WW0bPj8QQO
 zA4Z7yWlslvxcfY2BdJX3wD8klaINkl/8fDWZFFsBdfFX2VeLtm7Xfduw34BJpvU
 rYT3oWr6PhtkPAKR32SUcemSfeWgIVU41eSshzRz3kez1NngBUuLlSGGSEaKbes5
 pZVt6pYFFVByyf6MTHFEoQvafZfEw04JILZpo4R5V8iTHzom0kD3Py064sBiXEw2
 B6t+OW4qgcxGblpFkK2lD4kR2s1TPUs0ckVO6sAy1x8q60KKKjY=
 =vcbA
 -----END PGP SIGNATURE-----

Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...
This commit is contained in:
Linus Torvalds 2021-04-29 11:57:23 -07:00
commit 9d31d23389
1895 changed files with 121102 additions and 35070 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
Documentation/ABI/testing/sysfs-bus-pci
View File

@ -378,3 +378,32 @@ Description:
The value comes from the PCI kernel device state and can be one
of: "unknown", "error", "D0", D1", "D2", "D3hot", "D3cold".
The file is read only.
What: /sys/bus/pci/devices/.../sriov_vf_total_msix
Date: January 2021
Contact: Leon Romanovsky <leonro@nvidia.com>
Description:
This file is associated with a SR-IOV physical function (PF).
It contains the total number of MSI-X vectors available for
assignment to all virtual functions (VFs) associated with PF.
The value will be zero if the device doesn't support this
functionality. For supported devices, the value will be
constant and won't be changed after MSI-X vectors assignment.
What: /sys/bus/pci/devices/.../sriov_vf_msix_count
Date: January 2021
Contact: Leon Romanovsky <leonro@nvidia.com>
Description:
This file is associated with a SR-IOV virtual function (VF).
It allows configuration of the number of MSI-X vectors for
the VF. This allows devices that have a global pool of MSI-X
vectors to optimally divide them between VFs based on VF usage.
The values accepted are:
* > 0 - this number will be reported as the Table Size in the
VF's MSI-X capability
* < 0 - not valid
* = 0 - will reset to the device default value
The file is writable if the PF is bound to a driver that
implements ->sriov_set_msix_vec_count().

12
Documentation/ABI/testing/sysfs-class-net-phydev
View File

@ -51,3 +51,15 @@ Description:
Boolean value indicating whether the PHY device is used in
standalone mode, without a net_device associated, by PHYLINK.
Attribute created only when this is the case.
What: /sys/class/mdio_bus/<bus>/<device>/phy_dev_flags
Date: March 2021
KernelVersion: 5.13
Contact: netdev@vger.kernel.org
Description:
32-bit hexadecimal number representing a bit mask of the
configuration bits passed from the consumer of the PHY
(Ethernet MAC, switch, etc.) to the PHY driver. The flags are
only used internally by the kernel and their placement are
not meant to be stable across kernel versions. This is intended
for facilitating the debugging of PHY drivers.

11
Documentation/admin-guide/sysctl/net.rst
View File

@ -311,6 +311,17 @@ permit to distribute the load on several cpus.
If set to 1 (default), timestamps are sampled as soon as possible, before
queueing.
netdev_unregister_timeout_secs
------------------------------
Unregister network device timeout in seconds.
This option controls the timeout (in seconds) used to issue a warning while
waiting for a network device refcount to drop to 0 during device
unregistration. A lower value may be useful during bisection to detect
a leaked reference faster. A larger value may be useful to prevent false
warnings on slow/loaded systems.
Default value is 10, minimum 1, maximum 3600.
optmem_max
----------

15
Documentation/bpf/bpf_design_QA.rst
View File

@ -258,3 +258,18 @@ Q: Can BPF functionality such as new program or map types, new
helpers, etc be added out of kernel module code?
A: NO.
Q: Directly calling kernel function is an ABI?
----------------------------------------------
Q: Some kernel functions (e.g. tcp_slow_start) can be called
by BPF programs. Do these kernel functions become an ABI?
A: NO.
The kernel function protos will change and the bpf programs will be
rejected by the verifier. Also, for example, some of the bpf-callable
kernel functions have already been used by other kernel tcp
cc (congestion-control) implementations. If any of these kernel
functions has changed, both the in-tree and out-of-tree kernel tcp cc
implementations have to be changed. The same goes for the bpf
programs and they have to be adjusted accordingly.

30
Documentation/bpf/bpf_devel_QA.rst
View File

@ -29,7 +29,7 @@ list:
This may also include issues related to XDP, BPF tracing, etc.
Given netdev has a high volume of traffic, please also add the BPF
maintainers to Cc (from kernel MAINTAINERS_ file):
maintainers to Cc (from kernel ``MAINTAINERS`` file):
* Alexei Starovoitov <ast@kernel.org>
* Daniel Borkmann <daniel@iogearbox.net>
@ -234,11 +234,11 @@ be subject to change.
Q: samples/bpf preference vs selftests?
---------------------------------------
Q: When should I add code to `samples/bpf/`_ and when to BPF kernel
selftests_ ?
Q: When should I add code to ``samples/bpf/`` and when to BPF kernel
selftests_?
A: In general, we prefer additions to BPF kernel selftests_ rather than
`samples/bpf/`_. The rationale is very simple: kernel selftests are
``samples/bpf/``. The rationale is very simple: kernel selftests are
regularly run by various bots to test for kernel regressions.
The more test cases we add to BPF selftests, the better the coverage
@ -246,9 +246,9 @@ and the less likely it is that those could accidentally break. It is
not that BPF kernel selftests cannot demo how a specific feature can
be used.
That said, `samples/bpf/`_ may be a good place for people to get started,
That said, ``samples/bpf/`` may be a good place for people to get started,
so it might be advisable that simple demos of features could go into
`samples/bpf/`_, but advanced functional and corner-case testing rather
``samples/bpf/``, but advanced functional and corner-case testing rather
into kernel selftests.
If your sample looks like a test case, then go for BPF kernel selftests
@ -449,6 +449,19 @@ from source at
https://github.com/acmel/dwarves
pahole starts to use libbpf definitions and APIs since v1.13 after the
commit 21507cd3e97b ("pahole: add libbpf as submodule under lib/bpf").
It works well with the git repository because the libbpf submodule will
use "git submodule update --init --recursive" to update.
Unfortunately, the default github release source code does not contain
libbpf submodule source code and this will cause build issues, the tarball
from https://git.kernel.org/pub/scm/devel/pahole/pahole.git/ is same with
github, you can get the source tarball with corresponding libbpf submodule
codes from
https://fedorapeople.org/~acme/dwarves
Some distros have pahole version 1.16 packaged already, e.g.
Fedora, Gentoo.
@ -645,10 +658,9 @@ when:
.. Links
.. _Documentation/process/: https://www.kernel.org/doc/html/latest/process/
.. _MAINTAINERS: ../../MAINTAINERS
.. _netdev-FAQ: ../networking/netdev-FAQ.rst
.. _samples/bpf/: ../../samples/bpf/
.. _selftests: ../../tools/testing/selftests/bpf/
.. _selftests:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/
.. _Documentation/dev-tools/kselftest.rst:
https://www.kernel.org/doc/html/latest/dev-tools/kselftest.html
.. _Documentation/bpf/btf.rst: btf.rst

17
Documentation/bpf/btf.rst
View File

@ -84,6 +84,7 @@ sequentially and type id is assigned to each recognized type starting from id
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
#define BTF_KIND_VAR 14 /* Variable */
#define BTF_KIND_DATASEC 15 /* Section */
#define BTF_KIND_FLOAT 16 /* Floating point */
Note that the type section encodes debug info, not just pure types.
``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@ -95,8 +96,8 @@ Each type contains the following common data::
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
* bits 24-27: kind (e.g. int, ptr, array...etc)
* bits 28-30: unused
* bits 24-28: kind (e.g. int, ptr, array...etc)
* bits 29-30: unused
* bit 31: kind_flag, currently used by
* struct, union and fwd
*/
@ -452,6 +453,18 @@ map definition.
* ``offset``: the in-section offset of the variable
* ``size``: the size of the variable in bytes
2.2.16 BTF_KIND_FLOAT
~~~~~~~~~~~~~~~~~~~~~
``struct btf_type`` encoding requirement:
* ``name_off``: any valid offset
* ``info.kind_flag``: 0
* ``info.kind``: BTF_KIND_FLOAT
* ``info.vlen``: 0
* ``size``: the size of the float type in bytes: 2, 4, 8, 12 or 16.
No additional type data follow ``btf_type``.
3. BTF Kernel API
*****************

9
Documentation/bpf/index.rst
View File

@ -12,9 +12,6 @@ BPF instruction-set.
The Cilium project also maintains a `BPF and XDP Reference Guide`_
that goes into great technical depth about the BPF Architecture.
The primary info for the bpf syscall is available in the `man-pages`_
for `bpf(2)`_.
BPF Type Format (BTF)
=====================
@ -35,6 +32,12 @@ Two sets of Questions and Answers (Q&A) are maintained.
bpf_design_QA
bpf_devel_QA
Syscall API
===========
The primary info for the bpf syscall is available in the `man-pages`_
for `bpf(2)`_. For more information about the userspace API, see
Documentation/userspace-api/ebpf/index.rst.
Helper functions
================

92
Documentation/devicetree/bindings/net/actions,owl-emac.yaml Normal file
View File

@ -0,0 +1,92 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
%YAML 1.2
---
$id: http://devicetree.org/schemas/net/actions,owl-emac.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Actions Semi Owl SoCs Ethernet MAC Controller
maintainers:
- Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
description: |
This Ethernet MAC is used on the Owl family of SoCs from Actions Semi.
It provides the RMII and SMII interfaces and is compliant with the
IEEE 802.3 CSMA/CD standard, supporting both half-duplex and full-duplex
operation modes at 10/100 Mb/s data transfer rates.
allOf:
- $ref: "ethernet-controller.yaml#"
properties:
compatible:
oneOf:
- const: actions,owl-emac
- items:
- enum:
- actions,s500-emac
- const: actions,owl-emac
reg:
maxItems: 1
interrupts:
maxItems: 1
clocks:
minItems: 2
maxItems: 2
clock-names:
additionalItems: false
items:
- const: eth
- const: rmii
resets:
maxItems: 1
actions,ethcfg:
$ref: /schemas/types.yaml#/definitions/phandle
description:
Phandle to the device containing custom config.
required:
- compatible
- reg
- interrupts
- clocks
- clock-names
- resets
- phy-mode
- phy-handle
unevaluatedProperties: false
examples:
- |
#include <dt-bindings/clock/actions,s500-cmu.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/reset/actions,s500-reset.h>
ethernet@b0310000 {
compatible = "actions,s500-emac", "actions,owl-emac";
reg = <0xb0310000 0x10000>;
interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cmu 59 /*CLK_ETHERNET*/>, <&cmu CLK_RMII_REF>;
clock-names = "eth", "rmii";
resets = <&cmu RESET_ETHERNET>;
phy-mode = "rmii";
phy-handle = <&eth_phy>;
mdio {
#address-cells = <1>;
#size-cells = <0>;
eth_phy: ethernet-phy@3 {
reg = <0x3>;
interrupt-parent = <&sirq>;
interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
};
};
};

17
Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml
View File

@ -22,10 +22,18 @@ properties:
maxItems: 1
interrupts:
description: RX interrupt
minItems: 1
maxItems: 2
items:
- description: RX interrupt
- description: TX interrupt
interrupt-names:
const: rx
minItems: 1
maxItems: 2
items:
- const: rx
- const: tx
required:
- reg
@ -43,6 +51,7 @@ examples:
compatible = "brcm,bcm4908-enet";
reg = <0x80002000 0x1000>;
interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "rx";
interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "rx", "tx";
};

76
Documentation/devicetree/bindings/net/brcm,bcm6368-mdio-mux.yaml Normal file
View File

@ -0,0 +1,76 @@
# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
%YAML 1.2
---
$id: http://devicetree.org/schemas/net/brcm,bcm6368-mdio-mux.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Broadcom BCM6368 MDIO bus multiplexer
maintainers:
- Álvaro Fernández Rojas <noltari@gmail.com>
description:
This MDIO bus multiplexer defines buses that could be internal as well as
external to SoCs. When child bus is selected, one needs to select these two
properties as well to generate desired MDIO transaction on appropriate bus.
allOf:
- $ref: "mdio.yaml#"
properties:
compatible:
const: brcm,bcm6368-mdio-mux
"#address-cells":
const: 1
"#size-cells":
const: 0
reg:
maxItems: 1
required:
- compatible
- reg
patternProperties:
'^mdio@[0-1]$':
type: object
properties:
reg:
maxItems: 1
"#address-cells":
const: 1
"#size-cells":
const: 0
required:
- reg
- "#address-cells"
- "#size-cells"
unevaluatedProperties: false
examples:
- |
mdio0: mdio@10e000b0 {
#address-cells = <1>;
#size-cells = <0>;
compatible = "brcm,bcm6368-mdio-mux";
reg = <0x10e000b0 0x6>;
mdio_int: mdio@0 {
#address-cells = <1>;
#size-cells = <0>;
reg = <0>;
};
mdio_ext: mdio@1 {
#address-cells = <1>;
#size-cells = <0>;
reg = <1>;
};
};

56
Documentation/devicetree/bindings/net/broadcom-bluetooth.txt
View File

@ -1,56 +0,0 @@
Broadcom Bluetooth Chips
---------------------
This documents the binding structure and common properties for serial
attached Broadcom devices.
Serial attached Broadcom devices shall be a child node of the host UART
device the slave device is attached to.
Required properties:
- compatible: should contain one of the following:
* "brcm,bcm20702a1"
* "brcm,bcm4329-bt"
* "brcm,bcm4330-bt"
* "brcm,bcm43438-bt"
* "brcm,bcm4345c5"
* "brcm,bcm43540-bt"
* "brcm,bcm4335a0"
Optional properties:
- max-speed: see Documentation/devicetree/bindings/serial/serial.yaml
- shutdown-gpios: GPIO specifier, used to enable the BT module
- device-wakeup-gpios: GPIO specifier, used to wakeup the controller
- host-wakeup-gpios: GPIO specifier, used to wakeup the host processor.
deprecated, replaced by interrupts and
"host-wakeup" interrupt-names
- clocks: 1 or 2 clocks as defined in clock-names below, in that order
- clock-names: names for clock inputs, matching the clocks given
- "extclk": deprecated, replaced by "txco"
- "txco": external reference clock (not a standalone crystal)
- "lpo": external low power 32.768 kHz clock
- vbat-supply: phandle to regulator supply for VBAT
- vddio-supply: phandle to regulator supply for VDDIO
- brcm,bt-pcm-int-params: configure PCM parameters via a 5-byte array
- sco-routing: 0 = PCM, 1 = Transport, 2 = Codec, 3 = I2S
- pcm-interface-rate: 128KBps, 256KBps, 512KBps, 1024KBps, 2048KBps
- pcm-frame-type: short, long
- pcm-sync-mode: slave, master
- pcm-clock-mode: slave, master
- interrupts: must be one, used to wakeup the host processor
- interrupt-names: must be "host-wakeup"
Example:
&uart2 {
pinctrl-names = "default";
pinctrl-0 = <&uart2_pins>;
bluetooth {
compatible = "brcm,bcm43438-bt";
max-speed = <921600>;
brcm,bt-pcm-int-params = [01 02 00 01 01];
};
};

118
Documentation/devicetree/bindings/net/broadcom-bluetooth.yaml Normal file
View File

@ -0,0 +1,118 @@
# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
%YAML 1.2
---
$id: http://devicetree.org/schemas/net/broadcom-bluetooth.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Broadcom Bluetooth Chips
maintainers:
- Linus Walleij <linus.walleij@linaro.org>
description:
This binding describes Broadcom UART-attached bluetooth chips.
properties:
compatible:
enum:
- brcm,bcm20702a1
- brcm,bcm4329-bt
- brcm,bcm4330-bt
- brcm,bcm4334-bt
- brcm,bcm43438-bt
- brcm,bcm4345c5
- brcm,bcm43540-bt
- brcm,bcm4335a0
shutdown-gpios:
maxItems: 1
description: GPIO specifier for the line BT_REG_ON used to
power on the BT module
reset-gpios:
maxItems: 1
description: GPIO specifier for the line BT_RST_N used to
reset the BT module. This should be marked as
GPIO_ACTIVE_LOW.
device-wakeup-gpios:
maxItems: 1
description: GPIO specifier for the line BT_WAKE used to
wakeup the controller. This is using the BT_GPIO_0
pin on the chip when in use.
host-wakeup-gpios:
maxItems: 1
deprecated: true
description: GPIO specifier for the line HOST_WAKE used
to wakeup the host processor. This is using he BT_GPIO_1
pin on the chip when in use. This is deprecated and replaced
by interrupts and "host-wakeup" interrupt-names
clocks:
maxItems: 2
description: 1 or 2 clocks as defined in clock-names below,
in that order
clock-names:
description: Names of the 1 to 2 supplied clocks
items:
- const: txco
- const: lpo
- const: extclk
vbat-supply:
description: phandle to regulator supply for VBAT
vddio-supply:
description: phandle to regulator supply for VDDIO
brcm,bt-pcm-int-params:
$ref: /schemas/types.yaml#/definitions/uint8-array
minItems: 5
maxItems: 5
description: |-
configure PCM parameters via a 5-byte array:
sco-routing: 0 = PCM, 1 = Transport, 2 = Codec, 3 = I2S
pcm-interface-rate: 128KBps, 256KBps, 512KBps, 1024KBps, 2048KBps
pcm-frame-type: short, long
pcm-sync-mode: slave, master
pcm-clock-mode: slave, master
interrupts:
items:
- description: Handle to the line HOST_WAKE used to wake
up the host processor. This uses the BT_GPIO_1 pin on
the chip when in use.
interrupt-names:
items:
- const: host-wakeup
max-speed: true
current-speed: true
required:
- compatible
additionalProperties: false
examples:
- |
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/interrupt-controller/irq.h>
uart {
uart-has-rtscts;
bluetooth {
compatible = "brcm,bcm4330-bt";
max-speed = <921600>;
brcm,bt-pcm-int-params = [01 02 00 01 01];
shutdown-gpios = <&gpio 30 GPIO_ACTIVE_HIGH>;
device-wakeup-gpios = <&gpio 7 GPIO_ACTIVE_HIGH>;
reset-gpios = <&gpio 9 GPIO_ACTIVE_LOW>;
interrupt-parent = <&gpio>;
interrupts = <8 IRQ_TYPE_EDGE_FALLING>;
};
};

5
Documentation/devicetree/bindings/net/can/rcar_can.txt
View File

@ -19,7 +19,8 @@ Required properties:
"renesas,can-r8a7793" if CAN controller is a part of R8A7793 SoC.
"renesas,can-r8a7794" if CAN controller is a part of R8A7794 SoC.
"renesas,can-r8a7795" if CAN controller is a part of R8A7795 SoC.
"renesas,can-r8a7796" if CAN controller is a part of R8A7796 SoC.
"renesas,can-r8a7796" if CAN controller is a part of R8A77960 SoC.
"renesas,can-r8a77961" if CAN controller is a part of R8A77961 SoC.
"renesas,can-r8a77965" if CAN controller is a part of R8A77965 SoC.
"renesas,can-r8a77990" if CAN controller is a part of R8A77990 SoC.
"renesas,can-r8a77995" if CAN controller is a part of R8A77995 SoC.
@ -40,7 +41,7 @@ Required properties:
- pinctrl-names: must be "default".
Required properties for R8A774A1, R8A774B1, R8A774C0, R8A774E1, R8A7795,
R8A7796, R8A77965, R8A77990, and R8A77995:
R8A77960, R8A77961, R8A77965, R8A77990, and R8A77995:
For the denoted SoCs, "clkp2" can be CANFD clock. This is a div6 clock and can
be used by both CAN and CAN FD controller at the same time. It needs to be
scaled to maximum frequency if any of these controllers use it. This is done

9
Documentation/devicetree/bindings/net/dsa/dsa.yaml
View File

@ -70,6 +70,15 @@ patternProperties:
device is what the switch port is connected to
$ref: /schemas/types.yaml#/definitions/phandle
dsa-tag-protocol:
description:
Instead of the default, the switch will use this tag protocol if
possible. Useful when a device supports multiple protcols and
the default is incompatible with the Ethernet device.
enum:
- dsa
- edsa
phy-handle: true
phy-mode: true

4
Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt
View File

@ -5,6 +5,10 @@ Required properties for GSWIP core:
- compatible : "lantiq,xrx200-gswip" for the embedded GSWIP in the
xRX200 SoC
"lantiq,xrx300-gswip" for the embedded GSWIP in the
xRX300 SoC
"lantiq,xrx330-gswip" for the embedded GSWIP in the
xRX330 SoC
- reg : memory range of the GSWIP core registers
: memory range of the GSWIP MDIO registers
: memory range of the GSWIP MII registers

2
Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
View File

@ -21,6 +21,8 @@ properties:
- microchip,ksz8765
- microchip,ksz8794
- microchip,ksz8795
- microchip,ksz8863
- microchip,ksz8873
- microchip,ksz9477
- microchip,ksz9897
- microchip,ksz9896

15
Documentation/devicetree/bindings/net/fsl-enetc.txt
View File

@ -102,3 +102,18 @@ Example:
full-duplex;
};
};
* Integrated Endpoint Register Block bindings
Optionally, the fsl_enetc driver can probe on the Integrated Endpoint Register
Block, which preconfigures the FIFO limits for the ENETC ports. This is a node
with the following properties:
- reg : Specifies the address in the SoC memory space.
- compatible : Must be "fsl,ls1028a-enetc-ierb".
Example:
ierb@1f0800000 {
compatible = "fsl,ls1028a-enetc-ierb";
reg = <0x01 0xf0800000 0x0 0x10000>;
};

73
Documentation/devicetree/bindings/net/idt,3243x-emac.yaml Normal file
View File

@ -0,0 +1,73 @@
# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
%YAML 1.2
---
$id: http://devicetree.org/schemas/net/idt,3243x-emac.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: IDT 79rc3243x Ethernet controller
description: Ethernet controller integrated into IDT 79RC3243x family SoCs
maintainers:
- Thomas Bogendoerfer <tsbogend@alpha.franken.de>
allOf:
- $ref: ethernet-controller.yaml#
properties:
compatible:
const: idt,3243x-emac
reg:
maxItems: 3
reg-names:
items:
- const: emac
- const: dma_rx
- const: dma_tx
interrupts:
items:
- description: RX interrupt
- description: TX interrupt
interrupt-names:
items:
- const: rx
- const: tx
clocks:
maxItems: 1
clock-names:
items:
- const: mdioclk
required:
- compatible
- reg
- reg-names
- interrupts
- interrupt-names
additionalProperties: false
examples:
- |
ethernet@60000 {
compatible = "idt,3243x-emac";
reg = <0x60000 0x10000>,
<0x40000 0x14>,
<0x40014 0x14>;
reg-names = "emac", "dma_rx", "dma_tx";
interrupt-parent = <&rcpic3>;
interrupts = <0>, <1>;
interrupt-names = "rx", "tx";
clocks = <&iclk>;
clock-names = "mdioclk";
};

102
Documentation/devicetree/bindings/net/intel,ixp4xx-ethernet.yaml Normal file
View File

@ -0,0 +1,102 @@
# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
# Copyright 2018 Linaro Ltd.
%YAML 1.2
---
$id: "http://devicetree.org/schemas/net/intel,ixp4xx-ethernet.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Intel IXP4xx ethernet
allOf:
- $ref: "ethernet-controller.yaml#"
maintainers:
- Linus Walleij <linus.walleij@linaro.org>
description: |
The Intel IXP4xx ethernet makes use of the IXP4xx NPE (Network
Processing Engine) and the IXP4xx Queue Manager to process
the ethernet frames. It can optionally contain an MDIO bus to
talk to PHYs.
properties:
compatible:
const: intel,ixp4xx-ethernet
reg:
maxItems: 1
description: Ethernet MMIO address range
queue-rx:
$ref: '/schemas/types.yaml#/definitions/phandle-array'
maxItems: 1
description: phandle to the RX queue on the NPE
queue-txready:
$ref: '/schemas/types.yaml#/definitions/phandle-array'
maxItems: 1
description: phandle to the TX READY queue on the NPE
phy-mode: true
phy-handle: true
intel,npe-handle:
$ref: '/schemas/types.yaml#/definitions/phandle-array'
maxItems: 1
description: phandle to the NPE this ethernet instance is using
and the instance to use in the second cell
mdio:
type: object
$ref: "mdio.yaml#"
description: optional node for embedded MDIO controller
required:
- compatible
- reg
- queue-rx
- queue-txready
- intel,npe-handle
additionalProperties: false
examples:
- |
npe: npe@c8006000 {
compatible = "intel,ixp4xx-network-processing-engine";
reg = <0xc8006000 0x1000>, <0xc8007000 0x1000>, <0xc8008000 0x1000>;
};
ethernet@c8009000 {
compatible = "intel,ixp4xx-ethernet";
reg = <0xc8009000 0x1000>;
status = "disabled";
queue-rx = <&qmgr 4>;
queue-txready = <&qmgr 21>;
intel,npe-handle = <&npe 1>;
phy-mode = "rgmii";
phy-handle = <&phy1>;
};
ethernet@c800c000 {
compatible = "intel,ixp4xx-ethernet";
reg = <0xc800c000 0x1000>;
status = "disabled";
queue-rx = <&qmgr 3>;
queue-txready = <&qmgr 20>;
intel,npe-handle = <&npe 2>;
phy-mode = "rgmii";
phy-handle = <&phy2>;
mdio {
#address-cells = <1>;
#size-cells = <0>;
phy1: ethernet-phy@1 {
reg = <1>;
};
phy2: ethernet-phy@2 {
reg = <2>;
};
};
};

1
Documentation/devicetree/bindings/net/mdio-gpio.txt
View File

@ -2,6 +2,7 @@ MDIO on GPIOs
Currently defined compatibles:
- virtual,gpio-mdio
- microchip,mdio-smi0
MDC and MDIO lines connected to GPIO controllers are listed in the
gpios property as described in section VIII.1 in the following order:

26
Documentation/devicetree/bindings/net/qcom,ipa.yaml
View File

@ -43,7 +43,12 @@ description:
properties:
compatible:
const: "qcom,sdm845-ipa"
enum:
- qcom,sc7180-ipa
- qcom,sc7280-ipa
- qcom,sdm845-ipa
- qcom,sdx55-ipa
- qcom,sm8350-ipa
reg:
items:
@ -120,6 +125,14 @@ properties:
the firmware passed to Trust Zone for authentication. Required
when Trust Zone (not the modem) performs early initialization.
firmware-name:
$ref: /schemas/types.yaml#/definitions/string
description:
If present, name (or relative path) of the file within the
firmware search path containing the firmware image used when
initializing IPA hardware. Optional, and only used when
Trust Zone performs early initialization.
required:
- compatible
- iommus
@ -129,12 +142,23 @@ required:
- interconnects
- qcom,smem-states
# Either modem-init is present, or memory-region must be present.
oneOf:
- required:
- modem-init
- required:
- memory-region
# If memory-region is present, firmware-name may optionally be present.
# But if modem-init is present, firmware-name must not be present.
if:
required:
- modem-init
then:
not:
required:
- firmware-name
additionalProperties: false
examples:

11
Documentation/devicetree/bindings/net/renesas,etheravb.yaml
View File

@ -50,7 +50,16 @@ properties:
interrupt-names: true
clocks:
maxItems: 1
minItems: 1
maxItems: 2
items:
- description: AVB functional clock
- description: Optional TXC reference clock
clock-names:
items:
- const: fck
- const: refclk
iommus:
maxItems: 1

76
Documentation/devicetree/bindings/net/rockchip-dwmac.txt
View File

@ -1,76 +0,0 @@
Rockchip SoC RK3288 10/100/1000 Ethernet driver(GMAC)
The device node has following properties.
Required properties:
- compatible: should be "rockchip,<name>-gamc"
"rockchip,px30-gmac": found on PX30 SoCs
"rockchip,rk3128-gmac": found on RK312x SoCs
"rockchip,rk3228-gmac": found on RK322x SoCs
"rockchip,rk3288-gmac": found on RK3288 SoCs
"rockchip,rk3328-gmac": found on RK3328 SoCs
"rockchip,rk3366-gmac": found on RK3366 SoCs
"rockchip,rk3368-gmac": found on RK3368 SoCs
"rockchip,rk3399-gmac": found on RK3399 SoCs
"rockchip,rv1108-gmac": found on RV1108 SoCs
- reg: addresses and length of the register sets for the device.
- interrupts: Should contain the GMAC interrupts.
- interrupt-names: Should contain the interrupt names "macirq".
- rockchip,grf: phandle to the syscon grf used to control speed and mode.
- clocks: <&cru SCLK_MAC>: clock selector for main clock, from PLL or PHY.
<&cru SCLK_MAC_PLL>: PLL clock for SCLK_MAC
<&cru SCLK_MAC_RX>: clock gate for RX
<&cru SCLK_MAC_TX>: clock gate for TX
<&cru SCLK_MACREF>: clock gate for RMII referce clock
<&cru SCLK_MACREF_OUT> clock gate for RMII reference clock output
<&cru ACLK_GMAC>: AXI clock gate for GMAC
<&cru PCLK_GMAC>: APB clock gate for GMAC
- clock-names: One name for each entry in the clocks property.
- phy-mode: See ethernet.txt file in the same directory.
- pinctrl-names: Names corresponding to the numbered pinctrl states.
- pinctrl-0: pin-control mode. can be <&rgmii_pins> or <&rmii_pins>.
- clock_in_out: For RGMII, it must be "input", means main clock(125MHz)
is not sourced from SoC's PLL, but input from PHY; For RMII, "input" means
PHY provides the reference clock(50MHz), "output" means GMAC provides the
reference clock.
- snps,reset-gpio gpio number for phy reset.
- snps,reset-active-low boolean flag to indicate if phy reset is active low.
- assigned-clocks: main clock, should be <&cru SCLK_MAC>;
- assigned-clock-parents = parent of main clock.
can be <&ext_gmac> or <&cru SCLK_MAC_PLL>.
Optional properties:
- tx_delay: Delay value for TXD timing. Range value is 0~0x7F, 0x30 as default.
- rx_delay: Delay value for RXD timing. Range value is 0~0x7F, 0x10 as default.
- phy-supply: phandle to a regulator if the PHY needs one
Example:
gmac: ethernet@ff290000 {
compatible = "rockchip,rk3288-gmac";
reg = <0xff290000 0x10000>;
interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "macirq";
rockchip,grf = <&grf>;
clocks = <&cru SCLK_MAC>,
<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
<&cru SCLK_MACREF>, <&cru SCLK_MACREF_OUT>,
<&cru ACLK_GMAC>, <&cru PCLK_GMAC>;
clock-names = "stmmaceth",
"mac_clk_rx", "mac_clk_tx",
"clk_mac_ref", "clk_mac_refout",
"aclk_mac", "pclk_mac";
phy-mode = "rgmii";
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins /*&rmii_pins*/>;
clock_in_out = "input";
snps,reset-gpio = <&gpio4 7 0>;
snps,reset-active-low;
assigned-clocks = <&cru SCLK_MAC>;
assigned-clock-parents = <&ext_gmac>;
tx_delay = <0x30>;
rx_delay = <0x10>;
};

120
Documentation/devicetree/bindings/net/rockchip-dwmac.yaml Normal file
View File

@ -0,0 +1,120 @@
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
$id: "http://devicetree.org/schemas/net/rockchip-dwmac.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Rockchip 10/100/1000 Ethernet driver(GMAC)
maintainers:
- David Wu <david.wu@rock-chips.com>
# We need a select here so we don't match all nodes with 'snps,dwmac'
select:
properties:
compatible:
contains:
enum:
- rockchip,px30-gmac
- rockchip,rk3128-gmac
- rockchip,rk3228-gmac
- rockchip,rk3288-gmac
- rockchip,rk3328-gmac
- rockchip,rk3366-gmac
- rockchip,rk3368-gmac
- rockchip,rk3399-gmac
- rockchip,rv1108-gmac
required:
- compatible
allOf:
- $ref: "snps,dwmac.yaml#"
properties:
compatible:
items:
- enum:
- rockchip,px30-gmac
- rockchip,rk3128-gmac
- rockchip,rk3228-gmac
- rockchip,rk3288-gmac
- rockchip,rk3328-gmac
- rockchip,rk3366-gmac
- rockchip,rk3368-gmac
- rockchip,rk3399-gmac
- rockchip,rv1108-gmac
clocks:
minItems: 5
maxItems: 8
clock-names:
contains:
enum:
- stmmaceth
- mac_clk_tx
- mac_clk_rx
- aclk_mac
- pclk_mac
- clk_mac_ref
- clk_mac_refout
- clk_mac_speed
clock_in_out:
description:
For RGMII, it must be "input", means main clock(125MHz)
is not sourced from SoC's PLL, but input from PHY.
For RMII, "input" means PHY provides the reference clock(50MHz),
"output" means GMAC provides the reference clock.
$ref: /schemas/types.yaml#/definitions/string
enum: [input, output]
rockchip,grf:
description: The phandle of the syscon node for the general register file.
$ref: /schemas/types.yaml#/definitions/phandle
tx_delay:
description: Delay value for TXD timing. Range value is 0~0x7F, 0x30 as default.
$ref: /schemas/types.yaml#/definitions/uint32
rx_delay:
description: Delay value for RXD timing. Range value is 0~0x7F, 0x10 as default.
$ref: /schemas/types.yaml#/definitions/uint32
phy-supply:
description: PHY regulator
required:
- compatible
- clocks
- clock-names
unevaluatedProperties: false
examples:
- |
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/clock/rk3288-cru.h>
gmac: ethernet@ff290000 {
compatible = "rockchip,rk3288-gmac";
reg = <0xff290000 0x10000>;
interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "macirq";
clocks = <&cru SCLK_MAC>,
<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
<&cru SCLK_MACREF>, <&cru SCLK_MACREF_OUT>,
<&cru ACLK_GMAC>, <&cru PCLK_GMAC>;
clock-names = "stmmaceth",
"mac_clk_rx", "mac_clk_tx",
"clk_mac_ref", "clk_mac_refout",
"aclk_mac", "pclk_mac";
assigned-clocks = <&cru SCLK_MAC>;
assigned-clock-parents = <&ext_gmac>;
rockchip,grf = <&grf>;
phy-mode = "rgmii";
clock_in_out = "input";
tx_delay = <0x30>;
rx_delay = <0x10>;
};

13
Documentation/devicetree/bindings/net/snps,dwmac.yaml
View File

@ -56,6 +56,15 @@ properties:
- amlogic,meson8m2-dwmac
- amlogic,meson-gxbb-dwmac
- amlogic,meson-axg-dwmac
- rockchip,px30-gmac
- rockchip,rk3128-gmac
- rockchip,rk3228-gmac
- rockchip,rk3288-gmac
- rockchip,rk3328-gmac
- rockchip,rk3366-gmac
- rockchip,rk3368-gmac
- rockchip,rk3399-gmac
- rockchip,rv1108-gmac
- snps,dwmac
- snps,dwmac-3.50a
- snps,dwmac-3.610
@ -89,7 +98,7 @@ properties:
clocks:
minItems: 1
maxItems: 5
maxItems: 8
additionalItems: true
items:
- description: GMAC main clock
@ -101,7 +110,7 @@ properties:
clock-names:
minItems: 1
maxItems: 5
maxItems: 8
additionalItems: true
contains:
enum:

24
Documentation/devicetree/bindings/net/wireless/ieee80211.txt
View File

@ -1,24 +0,0 @@
Common IEEE 802.11 properties
This provides documentation of common properties that are valid for all wireless
devices.
Optional properties:
- ieee80211-freq-limit : list of supported frequency ranges in KHz. This can be
used for devices that in a given config support less channels than
normally. It may happen chipset supports a wide wireless band but it is
limited to some part of it due to used antennas or power amplifier.
An example case for this can be tri-band wireless router with two
identical chipsets used for two different 5 GHz subbands. Using them
incorrectly could not work or decrease performance noticeably.
Example:
pcie@0,0 {
reg = <0x0000 0 0 0 0>;
wifi@0,0 {
reg = <0x0000 0 0 0 0>;
ieee80211-freq-limit = <2402000 2482000>,
<5170000 5250000>;
};
};

45
Documentation/devicetree/bindings/net/wireless/ieee80211.yaml Normal file
View File

@ -0,0 +1,45 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
# Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
%YAML 1.2
---
$id: http://devicetree.org/schemas/net/wireless/ieee80211.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Common IEEE 802.11 Binding
maintainers:
- Lorenzo Bianconi <lorenzo@kernel.org>
description: |
This provides documentation of common properties that are valid for
all wireless devices
properties:
ieee80211-freq-limit:
$ref: /schemas/types.yaml#/definitions/uint32-matrix
items:
minItems: 2
maxItems: 2
description:
List of supported frequency ranges in KHz. This can be used for devices
that in a given config support less channels than normally. It may happen
chipset supports a wide wireless band but it is limited to some part of
it due to used antennas or power amplifier. An example case for this
can be tri-band wireless router with two identical chipsets used for two
different 5 GHz subbands. Using them incorrectly could not work or
decrease performance noticeably
additionalProperties: true
examples:
- |
pcie0 {
#address-cells = <3>;
#size-cells = <2>;
wifi@0,0 {
reg = <0x0000 0 0 0 0>;
ieee80211-freq-limit = <2402000 2482000>,
<5170000 5250000>;
};
};

78
Documentation/devicetree/bindings/net/wireless/mediatek,mt76.txt
View File

@ -1,78 +0,0 @@
* MediaTek mt76xx devices
This node provides properties for configuring the MediaTek mt76xx wireless
device. The node is expected to be specified as a child node of the PCI
controller to which the wireless chip is connected.
Alternatively, it can specify the wireless part of the MT7628/MT7688 or
MT7622 SoC. For SoC, use the following compatible strings:
compatible:
- "mediatek,mt7628-wmac" for MT7628/MT7688
- "mediatek,mt7622-wmac" for MT7622
properties:
- reg: Address and length of the register set for the device.
- interrupts: Main device interrupt
MT7622 specific properties:
- power-domains: phandle to the power domain that the WMAC is part of
- mediatek,infracfg: phandle to the infrastructure bus fabric syscon node
Optional properties:
- ieee80211-freq-limit: See ieee80211.txt
- mediatek,mtd-eeprom: Specify a MTD partition + offset containing EEPROM data
- big-endian: if the radio eeprom partition is written in big-endian, specify
this property
- mediatek,eeprom-merge-otp: Merge EEPROM data with OTP data. Can be used on
boards where the flash calibration data is generic and specific calibration
data should be pulled from the OTP ROM
The MAC address can as well be set with corresponding optional properties
defined in net/ethernet.txt.
Optional nodes:
- led: Properties for a connected LED
Optional properties:
- led-sources: See Documentation/devicetree/bindings/leds/common.txt
&pcie {
pcie0 {
wifi@0,0 {
compatible = "mediatek,mt76";
reg = <0x0000 0 0 0 0>;
ieee80211-freq-limit = <5000000 6000000>;
mediatek,mtd-eeprom = <&factory 0x8000>;
big-endian;
led {
led-sources = <2>;
};
};
};
};
MT7628 example:
wmac: wmac@10300000 {
compatible = "mediatek,mt7628-wmac";
reg = <0x10300000 0x100000>;
interrupt-parent = <&cpuintc>;
interrupts = <6>;
mediatek,mtd-eeprom = <&factory 0x0000>;
};
MT7622 example:
wmac: wmac@18000000 {
compatible = "mediatek,mt7622-wmac";
reg = <0 0x18000000 0 0x100000>;
interrupts = <GIC_SPI 211 IRQ_TYPE_LEVEL_LOW>;
mediatek,infracfg = <&infracfg>;
power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>;
};

228
Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml Normal file
View File

@ -0,0 +1,228 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
# Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
%YAML 1.2
---
$id: http://devicetree.org/schemas/net/wireless/mediatek,mt76.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: MediaTek mt76 wireless devices Generic Binding
maintainers:
- Felix Fietkau <nbd@nbd.name>
- Lorenzo Bianconi <lorenzo@kernel.org>
- Ryder Lee <ryder.lee@mediatek.com>
description: |
This node provides properties for configuring the MediaTek mt76xx
wireless device. The node is expected to be specified as a child
node of the PCI controller to which the wireless chip is connected.
Alternatively, it can specify the wireless part of the MT7628/MT7688
or MT7622 SoC.
allOf:
- $ref: ieee80211.yaml#
properties:
compatible:
enum:
- mediatek,mt76
- mediatek,mt7628-wmac
- mediatek,mt7622-wmac
reg:
maxItems: 1
interrupts:
maxItems: 1
power-domains:
maxItems: 1
mediatek,infracfg:
$ref: /schemas/types.yaml#/definitions/phandle
description:
Phandle to the infrastructure bus fabric syscon node.
This property is MT7622 specific
ieee80211-freq-limit: true
mediatek,mtd-eeprom:
$ref: /schemas/types.yaml#/definitions/phandle-array
description:
Phandle to a MTD partition + offset containing EEPROM data
big-endian:
$ref: /schemas/types.yaml#/definitions/flag
description:
Specify if the radio eeprom partition is written in big-endian
mediatek,eeprom-merge-otp:
type: boolean
description:
Merge EEPROM data with OTP data. Can be used on boards where the flash
calibration data is generic and specific calibration data should be
pulled from the OTP ROM
led:
type: object
$ref: /schemas/leds/common.yaml#
additionalProperties: false
properties:
led-sources:
maxItems: 1
power-limits:
type: object
additionalProperties: false
patternProperties:
"^r[0-9]+":
type: object
additionalProperties: false
properties:
regdomain:
$ref: /schemas/types.yaml#/definitions/string
description:
Regdomain refers to a legal regulatory region. Different
countries define different levels of allowable transmitter
power, time that a channel can be occupied, and different
available channels
enum:
- FCC
- ETSI
- JP
patternProperties:
"^txpower-[256]g$":
type: object
additionalProperties: false
patternProperties:
"^b[0-9]+$":
type: object
additionalProperties: false
properties:
channels:
$ref: /schemas/types.yaml#/definitions/uint32-array
minItems: 2
maxItems: 2
description:
Pairs of first and last channel number of the selected
band
rates-cck:
$ref: /schemas/types.yaml#/definitions/uint8-array
minItems: 4
maxItems: 4
description:
4 half-dBm per-rate power limit values
rates-ofdm:
$ref: /schemas/types.yaml#/definitions/uint8-array
minItems: 8
maxItems: 8
description:
8 half-dBm per-rate power limit values
rates-mcs:
$ref: /schemas/types.yaml#/definitions/uint8-matrix
description:
Sets of per-rate power limit values for 802.11n/802.11ac
rates for multiple channel bandwidth settings.
Each set starts with the number of channel bandwidth
settings for which the rate set applies, followed by
either 8 or 10 power limit values. The order of the
channel bandwidth settings is 20, 40, 80 and 160 MHz.
maxItems: 4
items:
minItems: 9
maxItems: 11
rates-ru:
$ref: /schemas/types.yaml#/definitions/uint8-matrix
description:
Sets of per-rate power limit values for 802.11ax rates
for multiple channel bandwidth or resource unit settings.
Each set starts with the number of channel bandwidth or
resource unit settings for which the rate set applies,
followed by 12 power limit values. The order of the
channel resource unit settings is RU26, RU52, RU106,
RU242/SU20, RU484/SU40, RU996/SU80 and RU2x996/SU160.
items:
minItems: 13
maxItems: 13
txs-delta:
$ref: /schemas/types.yaml#/definitions/uint32-array
description:
Half-dBm power delta for different numbers of antennas
required:
- compatible
- reg
additionalProperties: false
examples:
- |
pcie0 {
#address-cells = <3>;
#size-cells = <2>;
wifi@0,0 {
compatible = "mediatek,mt76";
reg = <0x0000 0 0 0 0>;
ieee80211-freq-limit = <5000000 6000000>;
mediatek,mtd-eeprom = <&factory 0x8000>;
big-endian;
led {
led-sources = <2>;
};
power-limits {
r0 {
regdomain = "FCC";
txpower-5g {
b0 {
channels = <36 48>;
rates-ofdm = /bits/ 8 <23 23 23 23 23 23 23 23>;
rates-mcs = /bits/ 8 <1 23 23 23 23 23 23 23 23 23 23>,
<3 22 22 22 22 22 22 22 22 22 22>;
rates-ru = /bits/ 8 <3 22 22 22 22 22 22 22 22 22 22 22 22>,
<4 20 20 20 20 20 20 20 20 20 20 20 20>;
};
b1 {
channels = <100 181>;
rates-ofdm = /bits/ 8 <14 14 14 14 14 14 14 14>;
rates-mcs = /bits/ 8 <4 14 14 14 14 14 14 14 14 14 14>;
txs-delta = <12 9 6>;
rates-ru = /bits/ 8 <7 14 14 14 14 14 14 14 14 14 14 14 14>;
};
};
};
};
};
};
- |
wifi@10300000 {
compatible = "mediatek,mt7628-wmac";
reg = <0x10300000 0x100000>;
interrupt-parent = <&cpuintc>;
interrupts = <6>;
mediatek,mtd-eeprom = <&factory 0x0>;
};
- |
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/interrupt-controller/irq.h>
wifi@18000000 {
compatible = "mediatek,mt7622-wmac";
reg = <0x10300000 0x100000>;
interrupts = <GIC_SPI 211 IRQ_TYPE_LEVEL_LOW>;
mediatek,infracfg = <&infracfg>;
power-domains = <&scpsys 3>;
};

25
Documentation/devicetree/bindings/net/xilinx_axienet.txt
View File

@ -42,11 +42,23 @@ Optional properties:
support both 1000BaseX and SGMII modes. If set, the phy-mode
should be set to match the mode selected on core reset (i.e.
by the basex_or_sgmii core input line).
- clocks : AXI bus clock for the device. Refer to common clock bindings.
Used to calculate MDIO clock divisor. If not specified, it is
auto-detected from the CPU clock (but only on platforms where
this is possible). New device trees should specify this - the
auto detection is only for backward compatibility.
- clock-names: Tuple listing input clock names. Possible clocks:
s_axi_lite_clk: Clock for AXI register slave interface
axis_clk: AXI4-Stream clock for TXD RXD TXC and RXS interfaces
ref_clk: Ethernet reference clock, used by signal delay
primitives and transceivers
mgt_clk: MGT reference clock (used by optional internal
PCS/PMA PHY)
Note that if s_axi_lite_clk is not specified by name, the
first clock of any name is used for this. If that is also not
specified, the clock rate is auto-detected from the CPU clock
(but only on platforms where this is possible). New device
trees should specify all applicable clocks by name - the
fallbacks to an unnamed clock or to CPU clock are only for
backward compatibility.
- clocks: Phandles to input clocks matching clock-names. Refer to common
clock bindings.
- axistream-connected: Reference to another node which contains the resources
for the AXI DMA controller used by this device.
If this is specified, the DMA-related resources from that
@ -62,7 +74,8 @@ Example:
device_type = "network";
interrupt-parent = <&microblaze_0_axi_intc>;
interrupts = <2 0 1>;
clocks = <&axi_clk>;
clock-names = "s_axi_lite_clk", "axis_clk", "ref_clk", "mgt_clk";
clocks = <&axi_clk>, <&axi_clk>, <&pl_enet_ref_clk>, <&mgt_clk>;
phy-mode = "mii";
reg = <0x40c00000 0x40000 0x50c00000 0x40000>;
xlnx,rxcsum = <0x2>;

2
Documentation/devicetree/bindings/serial/ingenic,uart.yaml
View File

@ -91,7 +91,7 @@ examples:
bluetooth {
compatible = "brcm,bcm4330-bt";
reset-gpios = <&gpf 8 GPIO_ACTIVE_HIGH>;
vcc-supply = <&wlan0_power>;
vbat-supply = <&wlan0_power>;
device-wakeup-gpios = <&gpf 5 GPIO_ACTIVE_HIGH>;
host-wakeup-gpios = <&gpf 6 GPIO_ACTIVE_HIGH>;
shutdown-gpios = <&gpf 4 GPIO_ACTIVE_LOW>;

2
Documentation/networking/can.rst
View File

@ -608,6 +608,8 @@ demand:
setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
&recv_own_msgs, sizeof(recv_own_msgs));
Note that reception of a socket's own CAN frames are subject to the same
filtering as other CAN frames (see :ref:`socketcan-rawfilter`).
.. _socketcan-rawfd:

34
Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
View File

@ -183,6 +183,40 @@ User command examples:
values:
cmode driverinit value true
esw_port_metadata: Eswitch port metadata state
----------------------------------------------
When applicable, disabling Eswitch metadata can increase packet rate
up to 20% depending on the use case and packet sizes.
Eswitch port metadata state controls whether to internally tag packets with
metadata. Metadata tagging must be enabled for multi-port RoCE, failover
between representors and stacked devices.
By default metadata is enabled on the supported devices in E-switch.
Metadata is applicable only for E-switch in switchdev mode and
users may disable it when NONE of the below use cases will be in use:
1. HCA is in Dual/multi-port RoCE mode.
2. VF/SF representor bonding (Usually used for Live migration)
3. Stacked devices
When metadata is disabled, the above use cases will fail to initialize if
users try to enable them.
- Show eswitch port metadata::
$ devlink dev param show pci/0000:06:00.0 name esw_port_metadata
pci/0000:06:00.0:
name esw_port_metadata type driver-specific
values:
cmode runtime value true
- Disable eswitch port metadata::
$ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime
- Change eswitch mode to switchdev mode where after choosing the metadata value::
$ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
mlx5 subfunction
================
mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface.

14
Documentation/networking/device_drivers/ethernet/microsoft/netvsc.rst
View File

@ -87,11 +87,15 @@ Receive Buffer
contain one or more packets. The number of receive sections may be changed
via ethtool Rx ring parameters.
There is a similar send buffer which is used to aggregate packets for sending.
The send area is broken into chunks of 6144 bytes, each of section may
contain one or more packets. The send buffer is an optimization, the driver
will use slower method to handle very large packets or if the send buffer
area is exhausted.
There is a similar send buffer which is used to aggregate packets
for sending. The send area is broken into chunks, typically of 6144
bytes, each of section may contain one or more packets. Small
packets are usually transmitted via copy to the send buffer. However,
if the buffer is temporarily exhausted, or the packet to be transmitted is
an LSO packet, the driver will provide the host with pointers to the data
from the SKB. This attempts to achieve a balance between the overhead of
data copy and the impact of remapping VM memory to be accessible by the
host.
XDP support
-----------

2
Documentation/networking/device_drivers/fddi/defza.rst
View File

@ -60,4 +60,4 @@ To do:
Both success and failure reports are welcome.
Maciej W. Rozycki <macro@linux-mips.org>
Maciej W. Rozycki <macro@orcam.me.uk>

17
Documentation/networking/devlink/devlink-health.rst
View File

@ -24,7 +24,7 @@ attributes of the health reporting and recovery procedures.
The ``devlink`` health reporter:
Device driver creates a "health reporter" per each error/health type.
Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error)
Error/Health type can be a known/generic (e.g. PCI error, fw error, rx/tx error)
or unknown (driver specific).
For each registered health reporter a driver can issue error/health reports
asynchronously. All health reports handling is done by ``devlink``.
@ -48,6 +48,7 @@ Once an error is reported, devlink health will perform the following actions:
* Object dump is being taken and saved at the reporter instance (as long as
there is no other dump which is already stored)
* Auto recovery attempt is being done. Depends on:
- Auto-recovery configuration
- Grace period vs. time passed since last recover
@ -72,14 +73,18 @@ via ``devlink``, e.g per error type (per health reporter):
* - ``DEVLINK_CMD_HEALTH_REPORTER_SET``
- Allows reporter-related configuration setting.
* - ``DEVLINK_CMD_HEALTH_REPORTER_RECOVER``
- Triggers a reporter's recovery procedure.
- Triggers reporter's recovery procedure.
* - ``DEVLINK_CMD_HEALTH_REPORTER_TEST``
- Triggers a fake health event on the reporter. The effects of the test
event in terms of recovery flow should follow closely that of a real
event.
* - ``DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE``
- Retrieves diagnostics data from a reporter on a device.
- Retrieves current device state related to the reporter.
* - ``DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET``
- Retrieves the last stored dump. Devlink health
saves a single dump. If an dump is not already stored by the devlink
saves a single dump. If an dump is not already stored by devlink
for this reporter, devlink generates a new dump.
dump output is defined by the reporter.
Dump output is defined by the reporter.
* - ``DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR``
- Clears the last saved dump file for the specified reporter.
@ -93,7 +98,7 @@ The following diagram provides a general overview of ``devlink-health``::
+--------------------------+
|request for ops
|(diagnose,
mlx5_core devlink |recover,
driver devlink |recover,
|dump)
+--------+ +--------------------------+
| | | reporter| |

312
Documentation/networking/dsa/configuration.rst
View File

@ -34,8 +34,15 @@ interface. The CPU port is the switch port connected to an Ethernet MAC chip.
The corresponding linux Ethernet interface is called the master interface.
All other corresponding linux interfaces are called slave interfaces.
The slave interfaces depend on the master interface. They can only brought up,
when the master interface is up.
The slave interfaces depend on the master interface being up in order for them
to send or receive traffic. Prior to kernel v5.12, the state of the master
interface had to be managed explicitly by the user. Starting with kernel v5.12,
the behavior is as follows:
- when a DSA slave interface is brought up, the master interface is
automatically brought up.
- when the master interface is brought down, all DSA slave interfaces are
automatically brought down.
In this documentation the following Ethernet interfaces are used:
@ -78,79 +85,76 @@ The tagging based configuration is desired and supported by the majority of
DSA switches. These switches are capable to tag incoming and outgoing traffic
without using a VLAN based configuration.
single port
~~~~~~~~~~~
*single port*
.. code-block:: sh
.. code-block:: sh
# configure each interface
ip addr add 192.0.2.1/30 dev lan1
ip addr add 192.0.2.5/30 dev lan2
ip addr add 192.0.2.9/30 dev lan3
# configure each interface
ip addr add 192.0.2.1/30 dev lan1
ip addr add 192.0.2.5/30 dev lan2
ip addr add 192.0.2.9/30 dev lan3
# For kernels earlier than v5.12, the master interface needs to be
# brought up manually before the slave ports.
ip link set eth0 up
# The master interface needs to be brought up before the slave ports.
ip link set eth0 up
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
*bridge*
.. code-block:: sh
bridge
~~~~~~
# For kernels earlier than v5.12, the master interface needs to be
# brought up manually before the slave ports.
ip link set eth0 up
.. code-block:: sh
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# The master interface needs to be brought up before the slave ports.
ip link set eth0 up
# create bridge
ip link add name br0 type bridge
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# add ports to bridge
ip link set dev lan1 master br0
ip link set dev lan2 master br0
ip link set dev lan3 master br0
# create bridge
ip link add name br0 type bridge
# configure the bridge
ip addr add 192.0.2.129/25 dev br0
# add ports to bridge
ip link set dev lan1 master br0
ip link set dev lan2 master br0
ip link set dev lan3 master br0
# bring up the bridge
ip link set dev br0 up
# configure the bridge
ip addr add 192.0.2.129/25 dev br0
*gateway*
.. code-block:: sh
# bring up the bridge
ip link set dev br0 up
# For kernels earlier than v5.12, the master interface needs to be
# brought up manually before the slave ports.
ip link set eth0 up
gateway
~~~~~~~
# bring up the slave interfaces
ip link set wan up
ip link set lan1 up
ip link set lan2 up
.. code-block:: sh
# configure the upstream port
ip addr add 192.0.2.1/30 dev wan
# The master interface needs to be brought up before the slave ports.
ip link set eth0 up
# create bridge
ip link add name br0 type bridge
# bring up the slave interfaces
ip link set wan up
ip link set lan1 up
ip link set lan2 up
# add ports to bridge
ip link set dev lan1 master br0
ip link set dev lan2 master br0
# configure the upstream port
ip addr add 192.0.2.1/30 dev wan
# configure the bridge
ip addr add 192.0.2.129/25 dev br0
# create bridge
ip link add name br0 type bridge
# add ports to bridge
ip link set dev lan1 master br0
ip link set dev lan2 master br0
# configure the bridge
ip addr add 192.0.2.129/25 dev br0
# bring up the bridge
ip link set dev br0 up
# bring up the bridge
ip link set dev br0 up
.. _dsa-vlan-configuration:
@ -161,132 +165,130 @@ A minority of switches are not capable to use a taging protocol
(DSA_TAG_PROTO_NONE). These switches can be configured by a VLAN based
configuration.
single port
~~~~~~~~~~~
The configuration can only be set up via VLAN tagging and bridge setup.
*single port*
The configuration can only be set up via VLAN tagging and bridge setup.
.. code-block:: sh
.. code-block:: sh
# tag traffic on CPU port
ip link add link eth0 name eth0.1 type vlan id 1
ip link add link eth0 name eth0.2 type vlan id 2
ip link add link eth0 name eth0.3 type vlan id 3
# tag traffic on CPU port
ip link add link eth0 name eth0.1 type vlan id 1
ip link add link eth0 name eth0.2 type vlan id 2
ip link add link eth0 name eth0.3 type vlan id 3
# The master interface needs to be brought up before the slave ports.
ip link set eth0 up
ip link set eth0.1 up
ip link set eth0.2 up
ip link set eth0.3 up
# For kernels earlier than v5.12, the master interface needs to be
# brought up manually before the slave ports.
ip link set eth0 up
ip link set eth0.1 up
ip link set eth0.2 up
ip link set eth0.3 up
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# create bridge
ip link add name br0 type bridge
# create bridge
ip link add name br0 type bridge
# activate VLAN filtering
ip link set dev br0 type bridge vlan_filtering 1
# activate VLAN filtering
ip link set dev br0 type bridge vlan_filtering 1
# add ports to bridges
ip link set dev lan1 master br0
ip link set dev lan2 master br0
ip link set dev lan3 master br0
# add ports to bridges
ip link set dev lan1 master br0
ip link set dev lan2 master br0
ip link set dev lan3 master br0
# tag traffic on ports
bridge vlan add dev lan1 vid 1 pvid untagged
bridge vlan add dev lan2 vid 2 pvid untagged
bridge vlan add dev lan3 vid 3 pvid untagged
# tag traffic on ports
bridge vlan add dev lan1 vid 1 pvid untagged
bridge vlan add dev lan2 vid 2 pvid untagged
bridge vlan add dev lan3 vid 3 pvid untagged
# configure the VLANs
ip addr add 192.0.2.1/30 dev eth0.1
ip addr add 192.0.2.5/30 dev eth0.2
ip addr add 192.0.2.9/30 dev eth0.3
# configure the VLANs
ip addr add 192.0.2.1/30 dev eth0.1
ip addr add 192.0.2.5/30 dev eth0.2
ip addr add 192.0.2.9/30 dev eth0.3
# bring up the bridge devices
ip link set br0 up
# bring up the bridge devices
ip link set br0 up
bridge
~~~~~~
*bridge*
.. code-block:: sh
.. code-block:: sh
# tag traffic on CPU port
ip link add link eth0 name eth0.1 type vlan id 1
# tag traffic on CPU port
ip link add link eth0 name eth0.1 type vlan id 1
# For kernels earlier than v5.12, the master interface needs to be
# brought up manually before the slave ports.
ip link set eth0 up
ip link set eth0.1 up
# The master interface needs to be brought up before the slave ports.
ip link set eth0 up
ip link set eth0.1 up
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# bring up the slave interfaces
ip link set lan1 up
ip link set lan2 up
ip link set lan3 up
# create bridge
ip link add name br0 type bridge
# create bridge
ip link add name br0 type bridge
# activate VLAN filtering
ip link set dev br0 type bridge vlan_filtering 1
# activate VLAN filtering
ip link set dev br0 type bridge vlan_filtering 1
# add ports to bridge
ip link set dev lan1 master br0
ip link set dev lan2 master br0
ip link set dev lan3 master br0
ip link set eth0.1 master br0
# add ports to bridge
ip link set dev lan1 master br0
ip link set dev lan2 master br0
ip link set dev lan3 master br0
ip link set eth0.1 master br0
# tag traffic on ports
bridge vlan add dev lan1 vid 1 pvid untagged
bridge vlan add dev lan2 vid 1 pvid untagged
bridge vlan add dev lan3 vid 1 pvid untagged
# tag traffic on ports
bridge vlan add dev lan1 vid 1 pvid untagged
bridge vlan add dev lan2 vid 1 pvid untagged
bridge vlan add dev lan3 vid 1 pvid untagged
# configure the bridge
ip addr add 192.0.2.129/25 dev br0
# configure the bridge
ip addr add 192.0.2.129/25 dev br0
# bring up the bridge
ip link set dev br0 up
# bring up the bridge
ip link set dev br0 up
*gateway*
.. code-block:: sh
gateway
~~~~~~~
# tag traffic on CPU port
ip link add link eth0 name eth0.1 type vlan id 1
ip link add link eth0 name eth0.2 type vlan id 2
.. code-block:: sh
# For kernels earlier than v5.12, the master interface needs to be
# brought up manually before the slave ports.
ip link set eth0 up
ip link set eth0.1 up
ip link set eth0.2 up
# tag traffic on CPU port
ip link add link eth0 name eth0.1 type vlan id 1
ip link add link eth0 name eth0.2 type vlan id 2
# bring up the slave interfaces
ip link set wan up
ip link set lan1 up
ip link set lan2 up
# The master interface needs to be brought up before the slave ports.
ip link set eth0 up
ip link set eth0.1 up
ip link set eth0.2 up
# create bridge
ip link add name br0 type bridge
# bring up the slave interfaces
ip link set wan up
ip link set lan1 up
ip link set lan2 up
# activate VLAN filtering
ip link set dev br0 type bridge vlan_filtering 1
# create bridge
ip link add name br0 type bridge
# add ports to bridges
ip link set dev wan master br0
ip link set eth0.1 master br0
ip link set dev lan1 master br0
ip link set dev lan2 master br0
# activate VLAN filtering
ip link set dev br0 type bridge vlan_filtering 1
# tag traffic on ports
bridge vlan add dev lan1 vid 1 pvid untagged
bridge vlan add dev lan2 vid 1 pvid untagged
bridge vlan add dev wan vid 2 pvid untagged
# add ports to bridges
ip link set dev wan master br0
ip link set eth0.1 master br0
ip link set dev lan1 master br0
ip link set dev lan2 master br0
# configure the VLANs
ip addr add 192.0.2.1/30 dev eth0.2
ip addr add 192.0.2.129/25 dev br0
# tag traffic on ports
bridge vlan add dev lan1 vid 1 pvid untagged
bridge vlan add dev lan2 vid 1 pvid untagged
bridge vlan add dev wan vid 2 pvid untagged
# configure the VLANs
ip addr add 192.0.2.1/30 dev eth0.2
ip addr add 192.0.2.129/25 dev br0
# bring up the bridge devices
ip link set br0 up
# bring up the bridge devices
ip link set br0 up

370
Documentation/networking/dsa/dsa.rst
View File

@ -65,14 +65,8 @@ Note that DSA does not currently create network interfaces for the "cpu" and
Switch tagging protocols
------------------------
DSA currently supports 5 different tagging protocols, and a tag-less mode as
well. The different protocols are implemented in:
- ``net/dsa/tag_trailer.c``: Marvell's 4 trailer tag mode (legacy)
- ``net/dsa/tag_dsa.c``: Marvell's original DSA tag
- ``net/dsa/tag_edsa.c``: Marvell's enhanced DSA tag
- ``net/dsa/tag_brcm.c``: Broadcom's 4 bytes tag
- ``net/dsa/tag_qca.c``: Qualcomm's 2 bytes tag
DSA supports many vendor-specific tagging protocols, one software-defined
tagging protocol, and a tag-less mode as well (``DSA_TAG_PROTO_NONE``).
The exact format of the tag protocol is vendor specific, but in general, they
all contain something which:
@ -80,6 +74,144 @@ all contain something which:
- identifies which port the Ethernet frame came from/should be sent to
- provides a reason why this frame was forwarded to the management interface
All tagging protocols are in ``net/dsa/tag_*.c`` files and implement the
methods of the ``struct dsa_device_ops`` structure, which are detailed below.
Tagging protocols generally fall in one of three categories:
1. The switch-specific frame header is located before the Ethernet header,
shifting to the right (from the perspective of the DSA master's frame
parser) the MAC DA, MAC SA, EtherType and the entire L2 payload.
2. The switch-specific frame header is located before the EtherType, keeping
the MAC DA and MAC SA in place from the DSA master's perspective, but
shifting the 'real' EtherType and L2 payload to the right.
3. The switch-specific frame header is located at the tail of the packet,
keeping all frame headers in place and not altering the view of the packet
that the DSA master's frame parser has.
A tagging protocol may tag all packets with switch tags of the same length, or
the tag length might vary (for example packets with PTP timestamps might
require an extended switch tag, or there might be one tag length on TX and a
different one on RX). Either way, the tagging protocol driver must populate the
``struct dsa_device_ops::overhead`` with the length in octets of the longest
switch frame header. The DSA framework will automatically adjust the MTU of the
master interface to accomodate for this extra size in order for DSA user ports
to support the standard MTU (L2 payload length) of 1500 octets. The ``overhead``
is also used to request from the network stack, on a best-effort basis, the
allocation of packets with a ``needed_headroom`` or ``needed_tailroom``
sufficient such that the act of pushing the switch tag on transmission of a
packet does not cause it to reallocate due to lack of memory.
Even though applications are not expected to parse DSA-specific frame headers,
the format on the wire of the tagging protocol represents an Application Binary
Interface exposed by the kernel towards user space, for decoders such as
``libpcap``. The tagging protocol driver must populate the ``proto`` member of
``struct dsa_device_ops`` with a value that uniquely describes the
characteristics of the interaction required between the switch hardware and the
data path driver: the offset of each bit field within the frame header and any
stateful processing required to deal with the frames (as may be required for
PTP timestamping).
From the perspective of the network stack, all switches within the same DSA
switch tree use the same tagging protocol. In case of a packet transiting a
fabric with more than one switch, the switch-specific frame header is inserted
by the first switch in the fabric that the packet was received on. This header
typically contains information regarding its type (whether it is a control
frame that must be trapped to the CPU, or a data frame to be forwarded).
Control frames should be decapsulated only by the software data path, whereas
data frames might also be autonomously forwarded towards other user ports of
other switches from the same fabric, and in this case, the outermost switch
ports must decapsulate the packet.
Note that in certain cases, it might be the case that the tagging format used
by a leaf switch (not connected directly to the CPU) to not be the same as what
the network stack sees. This can be seen with Marvell switch trees, where the
CPU port can be configured to use either the DSA or the Ethertype DSA (EDSA)
format, but the DSA links are configured to use the shorter (without Ethertype)
DSA frame header, in order to reduce the autonomous packet forwarding overhead.
It still remains the case that, if the DSA switch tree is configured for the
EDSA tagging protocol, the operating system sees EDSA-tagged packets from the
leaf switches that tagged them with the shorter DSA header. This can be done
because the Marvell switch connected directly to the CPU is configured to
perform tag translation between DSA and EDSA (which is simply the operation of
adding or removing the ``ETH_P_EDSA`` EtherType and some padding octets).
It is possible to construct cascaded setups of DSA switches even if their
tagging protocols are not compatible with one another. In this case, there are
no DSA links in this fabric, and each switch constitutes a disjoint DSA switch
tree. The DSA links are viewed as simply a pair of a DSA master (the out-facing
port of the upstream DSA switch) and a CPU port (the in-facing port of the
downstream DSA switch).
The tagging protocol of the attached DSA switch tree can be viewed through the
``dsa/tagging`` sysfs attribute of the DSA master::
cat /sys/class/net/eth0/dsa/tagging
If the hardware and driver are capable, the tagging protocol of the DSA switch
tree can be changed at runtime. This is done by writing the new tagging
protocol name to the same sysfs device attribute as above (the DSA master and
all attached switch ports must be down while doing this).
It is desirable that all tagging protocols are testable with the ``dsa_loop``
mockup driver, which can be attached to any network interface. The goal is that
any network interface should be capable of transmitting the same packet in the
same way, and the tagger should decode the same received packet in the same way
regardless of the driver used for the switch control path, and the driver used
for the DSA master.
The transmission of a packet goes through the tagger's ``xmit`` function.
The passed ``struct sk_buff *skb`` has ``skb->data`` pointing at
``skb_mac_header(skb)``, i.e. at the destination MAC address, and the passed
``struct net_device *dev`` represents the virtual DSA user network interface
whose hardware counterpart the packet must be steered to (i.e. ``swp0``).
The job of this method is to prepare the skb in a way that the switch will
understand what egress port the packet is for (and not deliver it towards other
ports). Typically this is fulfilled by pushing a frame header. Checking for
insufficient size in the skb headroom or tailroom is unnecessary provided that
the ``overhead`` and ``tail_tag`` properties were filled out properly, because
DSA ensures there is enough space before calling this method.
The reception of a packet goes through the tagger's ``rcv`` function. The
passed ``struct sk_buff *skb`` has ``skb->data`` pointing at
``skb_mac_header(skb) + ETH_ALEN`` octets, i.e. to where the first octet after
the EtherType would have been, were this frame not tagged. The role of this
method is to consume the frame header, adjust ``skb->data`` to really point at
the first octet after the EtherType, and to change ``skb->dev`` to point to the
virtual DSA user network interface corresponding to the physical front-facing
switch port that the packet was received on.
Since tagging protocols in category 1 and 2 break software (and most often also
hardware) packet dissection on the DSA master, features such as RPS (Receive
Packet Steering) on the DSA master would be broken. The DSA framework deals
with this by hooking into the flow dissector and shifting the offset at which
the IP header is to be found in the tagged frame as seen by the DSA master.
This behavior is automatic based on the ``overhead`` value of the tagging
protocol. If not all packets are of equal size, the tagger can implement the
``flow_dissect`` method of the ``struct dsa_device_ops`` and override this
default behavior by specifying the correct offset incurred by each individual
RX packet. Tail taggers do not cause issues to the flow dissector.
Due to various reasons (most common being category 1 taggers being associated
with DSA-unaware masters, mangling what the master perceives as MAC DA), the
tagging protocol may require the DSA master to operate in promiscuous mode, to
receive all frames regardless of the value of the MAC DA. This can be done by
setting the ``promisc_on_master`` property of the ``struct dsa_device_ops``.
Note that this assumes a DSA-unaware master driver, which is the norm.
Hardware manufacturers are strongly discouraged to do this, but some tagging
protocols might not provide source port information on RX for all packets, but
e.g. only for control traffic (link-local PDUs). In this case, by implementing
the ``filter`` method of ``struct dsa_device_ops``, the tagger might select
which packets are to be redirected on RX towards the virtual DSA user network
interfaces, and which are to be left in the DSA master's RX data path.
It might also happen (although silicon vendors are strongly discouraged to
produce hardware like this) that a tagging protocol splits the switch-specific
information into a header portion and a tail portion, therefore not falling
cleanly into any of the above 3 categories. DSA does not support this
configuration.
Master network devices
----------------------
@ -172,23 +304,34 @@ Graphical representation
Summarized, this is basically how DSA looks like from a network device
perspective::
|---------------------------
| CPU network device (eth0)|
----------------------------
| <tag added by switch |
| |
| |
| tag added by CPU> |
|--------------------------------------------|
| Switch driver |
|--------------------------------------------|
|| || ||
|-------| |-------| |-------|
| sw0p0 | | sw0p1 | | sw0p2 |
|-------| |-------| |-------|
Unaware application
opens and binds socket
| ^
| |
+-----------v--|--------------------+
|+------+ +------+ +------+ +------+|
|| swp0 | | swp1 | | swp2 | | swp3 ||
|+------+-+------+-+------+-+------+|
| DSA switch driver |
+-----------------------------------+
| ^
Tag added by | | Tag consumed by
switch driver | | switch driver
v |
+-----------------------------------+
| Unmodified host interface driver | Software
--------+-----------------------------------+------------
| Host interface (eth0) | Hardware
+-----------------------------------+
| ^
Tag consumed by | | Tag added by
switch hardware | | switch hardware
v |
+-----------------------------------+
| Switch |
|+------+ +------+ +------+ +------+|
|| swp0 | | swp1 | | swp2 | | swp3 ||
++------+-+------+-+------+-+------++
Slave MDIO bus
--------------
@ -239,14 +382,6 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as
Design limitations
==================
Limits on the number of devices and ports
-----------------------------------------
DSA currently limits the number of maximum switches within a tree to 4
(``DSA_MAX_SWITCHES``), and the number of ports per switch to 12 (``DSA_MAX_PORTS``).
These limits could be extended to support larger configurations would this need
arise.
Lack of CPU/DSA network devices
-------------------------------
@ -281,6 +416,7 @@ DSA currently leverages the following subsystems:
- MDIO/PHY library: ``drivers/net/phy/phy.c``, ``mdio_bus.c``
- Switchdev:``net/switchdev/*``
- Device Tree for various of_* functions
- Devlink: ``net/core/devlink.c``
MDIO/PHY library
----------------
@ -317,14 +453,39 @@ SWITCHDEV
DSA directly utilizes SWITCHDEV when interfacing with the bridge layer, and
more specifically with its VLAN filtering portion when configuring VLANs on top
of per-port slave network devices. Since DSA primarily deals with
MDIO-connected switches, although not exclusively, SWITCHDEV's
prepare/abort/commit phases are often simplified into a prepare phase which
checks whether the operation is supported by the DSA switch driver, and a commit
phase which applies the changes.
of per-port slave network devices. As of today, the only SWITCHDEV objects
supported by DSA are the FDB and VLAN objects.
As of today, the only SWITCHDEV objects supported by DSA are the FDB and VLAN
objects.
Devlink
-------
DSA registers one devlink device per physical switch in the fabric.
For each devlink device, every physical port (i.e. user ports, CPU ports, DSA
links or unused ports) is exposed as a devlink port.
DSA drivers can make use of the following devlink features:
- Regions: debugging feature which allows user space to dump driver-defined
areas of hardware information in a low-level, binary format. Both global
regions as well as per-port regions are supported. It is possible to export
devlink regions even for pieces of data that are already exposed in some way
to the standard iproute2 user space programs (ip-link, bridge), like address
tables and VLAN tables. For example, this might be useful if the tables
contain additional hardware-specific details which are not visible through
the iproute2 abstraction, or it might be useful to inspect these tables on
the non-user ports too, which are invisible to iproute2 because no network
interface is registered for them.
- Params: a feature which enables user to configure certain low-level tunable
knobs pertaining to the device. Drivers may implement applicable generic
devlink params, or may add new device-specific devlink params.
- Resources: a monitoring feature which enables users to see the degree of
utilization of certain hardware tables in the device, such as FDB, VLAN, etc.
- Shared buffers: a QoS feature for adjusting and partitioning memory and frame
reservations per port and per traffic class, in the ingress and egress
directions, such that low-priority bulk traffic does not impede the
processing of high-priority critical traffic.
For more details, consult ``Documentation/networking/devlink/``.
Device Tree
-----------
@ -490,6 +651,17 @@ Bridge layer
computing a STP state change based on current and asked parameters and perform
the relevant ageing based on the intersection results
- ``port_bridge_flags``: bridge layer function invoked when a port must
configure its settings for e.g. flooding of unknown traffic or source address
learning. The switch driver is responsible for initial setup of the
standalone ports with address learning disabled and egress flooding of all
types of traffic, then the DSA core notifies of any change to the bridge port
flags when the port joins and leaves a bridge. DSA does not currently manage
the bridge port flags for the CPU port. The assumption is that address
learning should be statically enabled (if supported by the hardware) on the
CPU port, and flooding towards the CPU port should also be enabled, due to a
lack of an explicit address filtering mechanism in the DSA core.
Bridge VLAN filtering
---------------------
@ -503,14 +675,10 @@ Bridge VLAN filtering
accept any 802.1Q frames irrespective of their VLAN ID, and untagged frames are
allowed.
- ``port_vlan_prepare``: bridge layer function invoked when the bridge prepares the
configuration of a VLAN on the given port. If the operation is not supported
by the hardware, this function should return ``-EOPNOTSUPP`` to inform the bridge
code to fallback to a software implementation. No hardware setup must be done
in this function. See port_vlan_add for this and details.
- ``port_vlan_add``: bridge layer function invoked when a VLAN is configured
(tagged or untagged) for the given switch port
(tagged or untagged) for the given switch port. If the operation is not
supported by the hardware, this function should return ``-EOPNOTSUPP`` to
inform the bridge code to fallback to a software implementation.
- ``port_vlan_del``: bridge layer function invoked when a VLAN is removed from the
given switch port
@ -538,14 +706,10 @@ Bridge VLAN filtering
function that the driver has to call for each MAC address known to be behind
the given port. A switchdev object is used to carry the VID and FDB info.
- ``port_mdb_prepare``: bridge layer function invoked when the bridge prepares the
installation of a multicast database entry. If the operation is not supported,
this function should return ``-EOPNOTSUPP`` to inform the bridge code to fallback
to a software implementation. No hardware setup must be done in this function.
See ``port_fdb_add`` for this and details.
- ``port_mdb_add``: bridge layer function invoked when the bridge wants to install
a multicast database entry, the switch hardware should be programmed with the
a multicast database entry. If the operation is not supported, this function
should return ``-EOPNOTSUPP`` to inform the bridge code to fallback to a
software implementation. The switch hardware should be programmed with the
specified address in the specified VLAN ID in the forwarding database
associated with this VLAN ID.
@ -561,6 +725,101 @@ Bridge VLAN filtering
function that the driver has to call for each MAC address known to be behind
the given port. A switchdev object is used to carry the VID and MDB info.
Link aggregation
----------------
Link aggregation is implemented in the Linux networking stack by the bonding
and team drivers, which are modeled as virtual, stackable network interfaces.
DSA is capable of offloading a link aggregation group (LAG) to hardware that
supports the feature, and supports bridging between physical ports and LAGs,
as well as between LAGs. A bonding/team interface which holds multiple physical
ports constitutes a logical port, although DSA has no explicit concept of a
logical port at the moment. Due to this, events where a LAG joins/leaves a
bridge are treated as if all individual physical ports that are members of that
LAG join/leave the bridge. Switchdev port attributes (VLAN filtering, STP
state, etc) and objects (VLANs, MDB entries) offloaded to a LAG as bridge port
are treated similarly: DSA offloads the same switchdev object / port attribute
on all members of the LAG. Static bridge FDB entries on a LAG are not yet
supported, since the DSA driver API does not have the concept of a logical port
ID.
- ``port_lag_join``: function invoked when a given switch port is added to a
LAG. The driver may return ``-EOPNOTSUPP``, and in this case, DSA will fall
back to a software implementation where all traffic from this port is sent to
the CPU.
- ``port_lag_leave``: function invoked when a given switch port leaves a LAG
and returns to operation as a standalone port.
- ``port_lag_change``: function invoked when the link state of any member of
the LAG changes, and the hashing function needs rebalancing to only make use
of the subset of physical LAG member ports that are up.
Drivers that benefit from having an ID associated with each offloaded LAG
can optionally populate ``ds->num_lag_ids`` from the ``dsa_switch_ops::setup``
method. The LAG ID associated with a bonding/team interface can then be
retrieved by a DSA switch driver using the ``dsa_lag_id`` function.
IEC 62439-2 (MRP)
-----------------
The Media Redundancy Protocol is a topology management protocol optimized for
fast fault recovery time for ring networks, which has some components
implemented as a function of the bridge driver. MRP uses management PDUs
(Test, Topology, LinkDown/Up, Option) sent at a multicast destination MAC
address range of 01:15:4e:00:00:0x and with an EtherType of 0x88e3.
Depending on the node's role in the ring (MRM: Media Redundancy Manager,
MRC: Media Redundancy Client, MRA: Media Redundancy Automanager), certain MRP
PDUs might need to be terminated locally and others might need to be forwarded.
An MRM might also benefit from offloading to hardware the creation and
transmission of certain MRP PDUs (Test).
Normally an MRP instance can be created on top of any network interface,
however in the case of a device with an offloaded data path such as DSA, it is
necessary for the hardware, even if it is not MRP-aware, to be able to extract
the MRP PDUs from the fabric before the driver can proceed with the software
implementation. DSA today has no driver which is MRP-aware, therefore it only
listens for the bare minimum switchdev objects required for the software assist
to work properly. The operations are detailed below.
- ``port_mrp_add`` and ``port_mrp_del``: notifies driver when an MRP instance
with a certain ring ID, priority, primary port and secondary port is
created/deleted.
- ``port_mrp_add_ring_role`` and ``port_mrp_del_ring_role``: function invoked
when an MRP instance changes ring roles between MRM or MRC. This affects
which MRP PDUs should be trapped to software and which should be autonomously
forwarded.
IEC 62439-3 (HSR/PRP)
---------------------
The Parallel Redundancy Protocol (PRP) is a network redundancy protocol which
works by duplicating and sequence numbering packets through two independent L2
networks (which are unaware of the PRP tail tags carried in the packets), and
eliminating the duplicates at the receiver. The High-availability Seamless
Redundancy (HSR) protocol is similar in concept, except all nodes that carry
the redundant traffic are aware of the fact that it is HSR-tagged (because HSR
uses a header with an EtherType of 0x892f) and are physically connected in a
ring topology. Both HSR and PRP use supervision frames for monitoring the
health of the network and for discovery of other nodes.
In Linux, both HSR and PRP are implemented in the hsr driver, which
instantiates a virtual, stackable network interface with two member ports.
The driver only implements the basic roles of DANH (Doubly Attached Node
implementing HSR) and DANP (Doubly Attached Node implementing PRP); the roles
of RedBox and QuadBox are not implemented (therefore, bridging a hsr network
interface with a physical switch port does not produce the expected result).
A driver which is able of offloading certain functions of a DANP or DANH should
declare the corresponding netdev features as indicated by the documentation at
``Documentation/networking/netdev-features.rst``. Additionally, the following
methods must be implemented:
- ``port_hsr_join``: function invoked when a given switch port is added to a
DANP/DANH. The driver may return ``-EOPNOTSUPP`` and in this case, DSA will
fall back to a software implementation where all traffic from this port is
sent to the CPU.
- ``port_hsr_leave``: function invoked when a given switch port leaves a
DANP/DANH and returns to normal operation as a standalone port.
TODO
====
@ -576,8 +835,5 @@ two subsystems and get the best of both worlds.
Other hanging fruits
--------------------
- making the number of ports fully dynamic and not dependent on ``DSA_MAX_PORTS``
- allowing more than one CPU/management interface:
http://comments.gmane.org/gmane.linux.network/365657
- porting more drivers from other vendors:
http://comments.gmane.org/gmane.linux.network/365510

269
Documentation/networking/ethtool-netlink.rst
View File

@ -208,41 +208,49 @@ Userspace to kernel:
``ETHTOOL_MSG_CABLE_TEST_ACT`` action start cable test
``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` action start raw TDR cable test
``ETHTOOL_MSG_TUNNEL_INFO_GET`` get tunnel offload info
``ETHTOOL_MSG_FEC_GET`` get FEC settings
``ETHTOOL_MSG_FEC_SET`` set FEC settings
``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM
``ETHTOOL_MSG_STATS_GET`` get standard statistics
===================================== ================================
Kernel to userspace:
===================================== =================================
``ETHTOOL_MSG_STRSET_GET_REPLY`` string set contents
``ETHTOOL_MSG_LINKINFO_GET_REPLY`` link settings
``ETHTOOL_MSG_LINKINFO_NTF`` link settings notification
``ETHTOOL_MSG_LINKMODES_GET_REPLY`` link modes info
``ETHTOOL_MSG_LINKMODES_NTF`` link modes notification
``ETHTOOL_MSG_LINKSTATE_GET_REPLY`` link state info
``ETHTOOL_MSG_DEBUG_GET_REPLY`` debugging settings
``ETHTOOL_MSG_DEBUG_NTF`` debugging settings notification
``ETHTOOL_MSG_WOL_GET_REPLY`` wake-on-lan settings
``ETHTOOL_MSG_WOL_NTF`` wake-on-lan settings notification
``ETHTOOL_MSG_FEATURES_GET_REPLY`` device features
``ETHTOOL_MSG_FEATURES_SET_REPLY`` optional reply to FEATURES_SET
``ETHTOOL_MSG_FEATURES_NTF`` netdev features notification
``ETHTOOL_MSG_PRIVFLAGS_GET_REPLY`` private flags
``ETHTOOL_MSG_PRIVFLAGS_NTF`` private flags
``ETHTOOL_MSG_RINGS_GET_REPLY`` ring sizes
``ETHTOOL_MSG_RINGS_NTF`` ring sizes
``ETHTOOL_MSG_CHANNELS_GET_REPLY`` channel counts
``ETHTOOL_MSG_CHANNELS_NTF`` channel counts
``ETHTOOL_MSG_COALESCE_GET_REPLY`` coalescing parameters
``ETHTOOL_MSG_COALESCE_NTF`` coalescing parameters
``ETHTOOL_MSG_PAUSE_GET_REPLY`` pause parameters
``ETHTOOL_MSG_PAUSE_NTF`` pause parameters
``ETHTOOL_MSG_EEE_GET_REPLY`` EEE settings
``ETHTOOL_MSG_EEE_NTF`` EEE settings
``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info
``ETHTOOL_MSG_CABLE_TEST_NTF`` Cable test results
``ETHTOOL_MSG_CABLE_TEST_TDR_NTF`` Cable test TDR results
``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info
===================================== =================================
======================================== =================================
``ETHTOOL_MSG_STRSET_GET_REPLY`` string set contents
``ETHTOOL_MSG_LINKINFO_GET_REPLY`` link settings
``ETHTOOL_MSG_LINKINFO_NTF`` link settings notification
``ETHTOOL_MSG_LINKMODES_GET_REPLY`` link modes info
``ETHTOOL_MSG_LINKMODES_NTF`` link modes notification
``ETHTOOL_MSG_LINKSTATE_GET_REPLY`` link state info
``ETHTOOL_MSG_DEBUG_GET_REPLY`` debugging settings
``ETHTOOL_MSG_DEBUG_NTF`` debugging settings notification
``ETHTOOL_MSG_WOL_GET_REPLY`` wake-on-lan settings
``ETHTOOL_MSG_WOL_NTF`` wake-on-lan settings notification
``ETHTOOL_MSG_FEATURES_GET_REPLY`` device features
``ETHTOOL_MSG_FEATURES_SET_REPLY`` optional reply to FEATURES_SET
``ETHTOOL_MSG_FEATURES_NTF`` netdev features notification
``ETHTOOL_MSG_PRIVFLAGS_GET_REPLY`` private flags
``ETHTOOL_MSG_PRIVFLAGS_NTF`` private flags
``ETHTOOL_MSG_RINGS_GET_REPLY`` ring sizes
``ETHTOOL_MSG_RINGS_NTF`` ring sizes
``ETHTOOL_MSG_CHANNELS_GET_REPLY`` channel counts
``ETHTOOL_MSG_CHANNELS_NTF`` channel counts
``ETHTOOL_MSG_COALESCE_GET_REPLY`` coalescing parameters
``ETHTOOL_MSG_COALESCE_NTF`` coalescing parameters
``ETHTOOL_MSG_PAUSE_GET_REPLY`` pause parameters
``ETHTOOL_MSG_PAUSE_NTF`` pause parameters
``ETHTOOL_MSG_EEE_GET_REPLY`` EEE settings
``ETHTOOL_MSG_EEE_NTF`` EEE settings
``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info
``ETHTOOL_MSG_CABLE_TEST_NTF`` Cable test results
``ETHTOOL_MSG_CABLE_TEST_TDR_NTF`` Cable test TDR results
``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info
``ETHTOOL_MSG_FEC_GET_REPLY`` FEC settings
``ETHTOOL_MSG_FEC_NTF`` FEC settings
``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM
``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics
======================================== =================================
``GET`` requests are sent by userspace applications to retrieve device
information. They usually do not contain any message specific attributes.
@ -1280,6 +1288,193 @@ Kernel response contents:
For UDP tunnel table empty ``ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES`` indicates that
the table contains static entries, hard-coded by the NIC.
FEC_GET
=======
Gets FEC configuration and state like ``ETHTOOL_GFECPARAM`` ioctl request.
Request contents:
===================================== ====== ==========================
``ETHTOOL_A_FEC_HEADER`` nested request header
===================================== ====== ==========================
Kernel response contents:
===================================== ====== ==========================
``ETHTOOL_A_FEC_HEADER`` nested request header
``ETHTOOL_A_FEC_MODES`` bitset configured modes
``ETHTOOL_A_FEC_AUTO`` bool FEC mode auto selection
``ETHTOOL_A_FEC_ACTIVE`` u32 index of active FEC mode
``ETHTOOL_A_FEC_STATS`` nested FEC statistics
===================================== ====== ==========================
``ETHTOOL_A_FEC_ACTIVE`` is the bit index of the FEC link mode currently
active on the interface. This attribute may not be present if device does
not support FEC.
``ETHTOOL_A_FEC_MODES`` and ``ETHTOOL_A_FEC_AUTO`` are only meaningful when
autonegotiation is disabled. If ``ETHTOOL_A_FEC_AUTO`` is non-zero driver will
select the FEC mode automatically based on the parameters of the SFP module.
This is equivalent to the ``ETHTOOL_FEC_AUTO`` bit of the ioctl interface.
``ETHTOOL_A_FEC_MODES`` carry the current FEC configuration using link mode
bits (rather than old ``ETHTOOL_FEC_*`` bits).
``ETHTOOL_A_FEC_STATS`` are reported if ``ETHTOOL_FLAG_STATS`` was set in
``ETHTOOL_A_HEADER_FLAGS``.
Each attribute carries an array of 64bit statistics. First entry in the array
contains the total number of events on the port, while the following entries
are counters corresponding to lanes/PCS instances. The number of entries in
the array will be:
+--------------+---------------------------------------------+
| `0` | device does not support FEC statistics |
+--------------+---------------------------------------------+
| `1` | device does not support per-lane break down |
+--------------+---------------------------------------------+
| `1 + #lanes` | device has full support for FEC stats |
+--------------+---------------------------------------------+
Drivers fill in the statistics in the following structure:
.. kernel-doc:: include/linux/ethtool.h
:identifiers: ethtool_fec_stats
FEC_SET
=======
Sets FEC parameters like ``ETHTOOL_SFECPARAM`` ioctl request.
Request contents:
===================================== ====== ==========================
``ETHTOOL_A_FEC_HEADER`` nested request header
``ETHTOOL_A_FEC_MODES`` bitset configured modes
``ETHTOOL_A_FEC_AUTO`` bool FEC mode auto selection
===================================== ====== ==========================
``FEC_SET`` is only meaningful when autonegotiation is disabled. Otherwise
FEC mode is selected as part of autonegotiation.
``ETHTOOL_A_FEC_MODES`` selects which FEC mode should be used. It's recommended
to set only one bit, if multiple bits are set driver may choose between them
in an implementation specific way.
``ETHTOOL_A_FEC_AUTO`` requests the driver to choose FEC mode based on SFP
module parameters. This does not mean autonegotiation.
MODULE_EEPROM
=============
Fetch module EEPROM data dump.
This interface is designed to allow dumps of at most 1/2 page at once. This
means only dumps of 128 (or less) bytes are allowed, without crossing half page
boundary located at offset 128. For pages other than 0 only high 128 bytes are
accessible.
Request contents:
======================================= ====== ==========================
``ETHTOOL_A_MODULE_EEPROM_HEADER`` nested request header
``ETHTOOL_A_MODULE_EEPROM_OFFSET`` u32 offset within a page
``ETHTOOL_A_MODULE_EEPROM_LENGTH`` u32 amount of bytes to read
``ETHTOOL_A_MODULE_EEPROM_PAGE`` u8 page number
``ETHTOOL_A_MODULE_EEPROM_BANK`` u8 bank number
``ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS`` u8 page I2C address
======================================= ====== ==========================
Kernel response contents:
+---------------------------------------------+--------+---------------------+
| ``ETHTOOL_A_MODULE_EEPROM_HEADER`` | nested | reply header |
+---------------------------------------------+--------+---------------------+
| ``ETHTOOL_A_MODULE_EEPROM_DATA`` | nested | array of bytes from |
| | | module EEPROM |
+---------------------------------------------+--------+---------------------+
``ETHTOOL_A_MODULE_EEPROM_DATA`` has an attribute length equal to the amount of
bytes driver actually read.
STATS_GET
=========
Get standard statistics for the interface. Note that this is not
a re-implementation of ``ETHTOOL_GSTATS`` which exposed driver-defined
stats.
Request contents:
======================================= ====== ==========================
``ETHTOOL_A_STATS_HEADER`` nested request header
``ETHTOOL_A_STATS_GROUPS`` bitset requested groups of stats
======================================= ====== ==========================
Kernel response contents:
+-----------------------------------+--------+--------------------------------+
| ``ETHTOOL_A_STATS_HEADER`` | nested | reply header |
+-----------------------------------+--------+--------------------------------+
| ``ETHTOOL_A_STATS_GRP`` | nested | one or more group of stats |
+-+---------------------------------+--------+--------------------------------+
| | ``ETHTOOL_A_STATS_GRP_ID`` | u32 | group ID - ``ETHTOOL_STATS_*`` |
+-+---------------------------------+--------+--------------------------------+
| | ``ETHTOOL_A_STATS_GRP_SS_ID`` | u32 | string set ID for names |
+-+---------------------------------+--------+--------------------------------+
| | ``ETHTOOL_A_STATS_GRP_STAT`` | nested | nest containing a statistic |
+-+---------------------------------+--------+--------------------------------+
| | ``ETHTOOL_A_STATS_GRP_HIST_RX`` | nested | histogram statistic (Rx) |
+-+---------------------------------+--------+--------------------------------+
| | ``ETHTOOL_A_STATS_GRP_HIST_TX`` | nested | histogram statistic (Tx) |
+-+---------------------------------+--------+--------------------------------+
Users specify which groups of statistics they are requesting via
the ``ETHTOOL_A_STATS_GROUPS`` bitset. Currently defined values are:
====================== ======== ===============================================
ETHTOOL_STATS_ETH_MAC eth-mac Basic IEEE 802.3 MAC statistics (30.3.1.1.*)
ETHTOOL_STATS_ETH_PHY eth-phy Basic IEEE 802.3 PHY statistics (30.3.2.1.*)
ETHTOOL_STATS_ETH_CTRL eth-ctrl Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*)
ETHTOOL_STATS_RMON rmon RMON (RFC 2819) statistics
====================== ======== ===============================================
Each group should have a corresponding ``ETHTOOL_A_STATS_GRP`` in the reply.
``ETHTOOL_A_STATS_GRP_ID`` identifies which group's statistics nest contains.
``ETHTOOL_A_STATS_GRP_SS_ID`` identifies the string set ID for the names of
the statistics in the group, if available.
Statistics are added to the ``ETHTOOL_A_STATS_GRP`` nest under
``ETHTOOL_A_STATS_GRP_STAT``. ``ETHTOOL_A_STATS_GRP_STAT`` should contain
single 8 byte (u64) attribute inside - the type of that attribute is
the statistic ID and the value is the value of the statistic.
Each group has its own interpretation of statistic IDs.
Attribute IDs correspond to strings from the string set identified
by ``ETHTOOL_A_STATS_GRP_SS_ID``. Complex statistics (such as RMON histogram
entries) are also listed inside ``ETHTOOL_A_STATS_GRP`` and do not have
a string defined in the string set.
RMON "histogram" counters count number of packets within given size range.
Because RFC does not specify the ranges beyond the standard 1518 MTU devices
differ in definition of buckets. For this reason the definition of packet ranges
is left to each driver.
``ETHTOOL_A_STATS_GRP_HIST_RX`` and ``ETHTOOL_A_STATS_GRP_HIST_TX`` nests
contain the following attributes:
================================= ====== ===================================
ETHTOOL_A_STATS_RMON_HIST_BKT_LOW u32 low bound of the packet size bucket
ETHTOOL_A_STATS_RMON_HIST_BKT_HI u32 high bound of the bucket
ETHTOOL_A_STATS_RMON_HIST_VAL u64 packet counter
================================= ====== ===================================
Low and high bounds are inclusive, for example:
============================= ==== ====
RFC statistic low high
============================= ==== ====
etherStatsPkts64Octets 0 64
etherStatsPkts512to1023Octets 512 1023
============================= ==== ====
Request translation
===================
@ -1357,8 +1552,8 @@ are netlink only.
``ETHTOOL_GET_DUMP_FLAG`` n/a
``ETHTOOL_GET_DUMP_DATA`` n/a
``ETHTOOL_GET_TS_INFO`` ``ETHTOOL_MSG_TSINFO_GET``
``ETHTOOL_GMODULEINFO`` n/a
``ETHTOOL_GMODULEEEPROM`` n/a
``ETHTOOL_GMODULEINFO`` ``ETHTOOL_MSG_MODULE_EEPROM_GET``
``ETHTOOL_GMODULEEEPROM`` ``ETHTOOL_MSG_MODULE_EEPROM_GET``
``ETHTOOL_GEEE`` ``ETHTOOL_MSG_EEE_GET``
``ETHTOOL_SEEE`` ``ETHTOOL_MSG_EEE_SET``
``ETHTOOL_GRSSH`` n/a
@ -1373,9 +1568,9 @@ are netlink only.
``ETHTOOL_MSG_LINKMODES_SET``
``ETHTOOL_PHY_GTUNABLE`` n/a
``ETHTOOL_PHY_STUNABLE`` n/a
``ETHTOOL_GFECPARAM`` n/a
``ETHTOOL_SFECPARAM`` n/a
n/a ''ETHTOOL_MSG_CABLE_TEST_ACT''
n/a ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT''
``ETHTOOL_GFECPARAM`` ``ETHTOOL_MSG_FEC_GET``
``ETHTOOL_SFECPARAM`` ``ETHTOOL_MSG_FEC_SET``
n/a ``ETHTOOL_MSG_CABLE_TEST_ACT``
n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``
n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET``
=================================== =====================================

2
Documentation/networking/filter.rst
View File

@ -327,7 +327,7 @@ Examples for low-level BPF:
ret #-1
drop: ret #0
**icmp random packet sampling, 1 in 4**:
**icmp random packet sampling, 1 in 4**::
ldh [12]
jne #0x800, drop

1
Documentation/networking/index.rst
View File

@ -76,6 +76,7 @@ Contents:
netdevices
netfilter-sysctl
netif-msg
nexthop-group-resilient
nf_conntrack-sysctl
nf_flowtable
openvswitch

10
Documentation/networking/ip-sysctl.rst
View File

@ -1073,7 +1073,9 @@ ip_local_reserved_ports - list of comma separated ranges
although this is redundant. However such a setting is useful
if later the port range is changed to a value that will
include the reserved ports.
include the reserved ports. Also keep in mind, that overlapping
of these ranges may affect probability of selecting ephemeral
ports which are right after block of reserved ports.
Default: Empty
@ -1143,6 +1145,12 @@ icmp_echo_ignore_all - BOOLEAN
Default: 0
icmp_echo_enable_probe - BOOLEAN
If set to one, then the kernel will respond to RFC 8335 PROBE
requests sent to it.
Default: 0
icmp_echo_ignore_broadcasts - BOOLEAN
If set non-zero, then the kernel will ignore all ICMP ECHO and
TIMESTAMP requests sent to it via broadcast/multicast.

293
Documentation/networking/nexthop-group-resilient.rst Normal file
View File

@ -0,0 +1,293 @@
.. SPDX-License-Identifier: GPL-2.0
=========================
Resilient Next-hop Groups
=========================
Resilient groups are a type of next-hop group that is aimed at minimizing
disruption in flow routing across changes to the group composition and
weights of constituent next hops.
The idea behind resilient hashing groups is best explained in contrast to
the legacy multipath next-hop group, which uses the hash-threshold
algorithm, described in RFC 2992.
To select a next hop, hash-threshold algorithm first assigns a range of
hashes to each next hop in the group, and then selects the next hop by
comparing the SKB hash with the individual ranges. When a next hop is
removed from the group, the ranges are recomputed, which leads to
reassignment of parts of hash space from one next hop to another. RFC 2992
illustrates it thus::
+-------+-------+-------+-------+-------+
| 1 | 2 | 3 | 4 | 5 |
+-------+-+-----+---+---+-----+-+-------+
| 1 | 2 | 4 | 5 |
+---------+---------+---------+---------+
Before and after deletion of next hop 3
under the hash-threshold algorithm.
Note how next hop 2 gave up part of the hash space in favor of next hop 1,
and 4 in favor of 5. While there will usually be some overlap between the
previous and the new distribution, some traffic flows change the next hop
that they resolve to.
If a multipath group is used for load-balancing between multiple servers,
this hash space reassignment causes an issue that packets from a single
flow suddenly end up arriving at a server that does not expect them. This
can result in TCP connections being reset.
If a multipath group is used for load-balancing among available paths to
the same server, the issue is that different latencies and reordering along
the way causes the packets to arrive in the wrong order, resulting in
degraded application performance.
To mitigate the above-mentioned flow redirection, resilient next-hop groups
insert another layer of indirection between the hash space and its
constituent next hops: a hash table. The selection algorithm uses SKB hash
to choose a hash table bucket, then reads the next hop that this bucket
contains, and forwards traffic there.
This indirection brings an important feature. In the hash-threshold
algorithm, the range of hashes associated with a next hop must be
continuous. With a hash table, mapping between the hash table buckets and
the individual next hops is arbitrary. Therefore when a next hop is deleted
the buckets that held it are simply reassigned to other next hops::
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|1|1|1|1|2|2|2|2|3|3|3|3|4|4|4|4|5|5|5|5|
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
v v v v
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|1|1|1|1|2|2|2|2|1|2|4|5|4|4|4|4|5|5|5|5|
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Before and after deletion of next hop 3
under the resilient hashing algorithm.
When weights of next hops in a group are altered, it may be possible to
choose a subset of buckets that are currently not used for forwarding
traffic, and use those to satisfy the new next-hop distribution demands,
keeping the "busy" buckets intact. This way, established flows are ideally
kept being forwarded to the same endpoints through the same paths as before
the next-hop group change.
Algorithm
---------
In a nutshell, the algorithm works as follows. Each next hop deserves a
certain number of buckets, according to its weight and the number of
buckets in the hash table. In accordance with the source code, we will call
this number a "wants count" of a next hop. In case of an event that might
cause bucket allocation change, the wants counts for individual next hops
are updated.
Next hops that have fewer buckets than their wants count, are called
"underweight". Those that have more are "overweight". If there are no
overweight (and therefore no underweight) next hops in the group, it is
said to be "balanced".
Each bucket maintains a last-used timer. Every time a packet is forwarded
through a bucket, this timer is updated to current jiffies value. One
attribute of a resilient group is then the "idle timer", which is the
amount of time that a bucket must not be hit by traffic in order for it to
be considered "idle". Buckets that are not idle are busy.
After assigning wants counts to next hops, an "upkeep" algorithm runs. For
buckets:
1) that have no assigned next hop, or
2) whose next hop has been removed, or
3) that are idle and their next hop is overweight,
upkeep changes the next hop that the bucket references to one of the
underweight next hops. If, after considering all buckets in this manner,
there are still underweight next hops, another upkeep run is scheduled to a
future time.
There may not be enough "idle" buckets to satisfy the updated wants counts
of all next hops. Another attribute of a resilient group is the "unbalanced
timer". This timer can be set to 0, in which case the table will stay out
of balance until idle buckets do appear, possibly never. If set to a
non-zero value, the value represents the period of time that the table is
permitted to stay out of balance.
With this in mind, we update the above list of conditions with one more
item. Thus buckets:
4) whose next hop is overweight, and the amount of time that the table has
been out of balance exceeds the unbalanced timer, if that is non-zero,
\... are migrated as well.
Offloading & Driver Feedback
----------------------------
When offloading resilient groups, the algorithm that distributes buckets
among next hops is still the one in SW. Drivers are notified of updates to
next hop groups in the following three ways:
- Full group notification with the type
``NH_NOTIFIER_INFO_TYPE_RES_TABLE``. This is used just after the group is
created and buckets populated for the first time.
- Single-bucket notifications of the type
``NH_NOTIFIER_INFO_TYPE_RES_BUCKET``, which is used for notifications of
individual migrations within an already-established group.
- Pre-replace notification, ``NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE``. This
is sent before the group is replaced, and is a way for the driver to veto
the group before committing anything to the HW.
Some single-bucket notifications are forced, as indicated by the "force"
flag in the notification. Those are used for the cases where e.g. the next
hop associated with the bucket was removed, and the bucket really must be
migrated.
Non-forced notifications can be overridden by the driver by returning an
error code. The use case for this is that the driver notifies the HW that a
bucket should be migrated, but the HW discovers that the bucket has in fact
been hit by traffic.
A second way for the HW to report that a bucket is busy is through the
``nexthop_res_grp_activity_update()`` API. The buckets identified this way
as busy are treated as if traffic hit them.
Offloaded buckets should be flagged as either "offload" or "trap". This is
done through the ``nexthop_bucket_set_hw_flags()`` API.
Netlink UAPI
------------
Resilient Group Replacement
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Resilient groups are configured using the ``RTM_NEWNEXTHOP`` message in the
same manner as other multipath groups. The following changes apply to the
attributes passed in the netlink message:
=================== =========================================================
``NHA_GROUP_TYPE`` Should be ``NEXTHOP_GRP_TYPE_RES`` for resilient group.
``NHA_RES_GROUP`` A nest that contains attributes specific to resilient
groups.
=================== =========================================================
``NHA_RES_GROUP`` payload:
=================================== =========================================
``NHA_RES_GROUP_BUCKETS`` Number of buckets in the hash table.
``NHA_RES_GROUP_IDLE_TIMER`` Idle timer in units of clock_t.
``NHA_RES_GROUP_UNBALANCED_TIMER`` Unbalanced timer in units of clock_t.
=================================== =========================================
Next Hop Get
^^^^^^^^^^^^
Requests to get resilient next-hop groups use the ``RTM_GETNEXTHOP``
message in exactly the same way as other next hop get requests. The
response attributes match the replacement attributes cited above, except
``NHA_RES_GROUP`` payload will include the following attribute:
=================================== =========================================
``NHA_RES_GROUP_UNBALANCED_TIME`` How long has the resilient group been out
of balance, in units of clock_t.
=================================== =========================================
Bucket Get
^^^^^^^^^^
The message ``RTM_GETNEXTHOPBUCKET`` without the ``NLM_F_DUMP`` flag is
used to request a single bucket. The attributes recognized at get requests
are:
=================== =========================================================
``NHA_ID`` ID of the next-hop group that the bucket belongs to.
``NHA_RES_BUCKET`` A nest that contains attributes specific to bucket.
=================== =========================================================
``NHA_RES_BUCKET`` payload:
======================== ====================================================
``NHA_RES_BUCKET_INDEX`` Index of bucket in the resilient table.
======================== ====================================================
Bucket Dumps
^^^^^^^^^^^^
The message ``RTM_GETNEXTHOPBUCKET`` with the ``NLM_F_DUMP`` flag is used
to request a dump of matching buckets. The attributes recognized at dump
requests are:
=================== =========================================================
``NHA_ID`` If specified, limits the dump to just the next-hop group
with this ID.
``NHA_OIF`` If specified, limits the dump to buckets that contain
next hops that use the device with this ifindex.
``NHA_MASTER`` If specified, limits the dump to buckets that contain
next hops that use a device in the VRF with this ifindex.
``NHA_RES_BUCKET`` A nest that contains attributes specific to bucket.
=================== =========================================================
``NHA_RES_BUCKET`` payload:
======================== ====================================================
``NHA_RES_BUCKET_NH_ID`` If specified, limits the dump to just the buckets
that contain the next hop with this ID.
======================== ====================================================
Usage
-----
To illustrate the usage, consider the following commands::
# ip nexthop add id 1 via 192.0.2.2 dev eth0
# ip nexthop add id 2 via 192.0.2.3 dev eth0
# ip nexthop add id 10 group 1/2 type resilient \
buckets 8 idle_timer 60 unbalanced_timer 300
The last command creates a resilient next-hop group. It will have 8 buckets
(which is unusually low number, and used here for demonstration purposes
only), each bucket will be considered idle when no traffic hits it for at
least 60 seconds, and if the table remains out of balance for 300 seconds,
it will be forcefully brought into balance.
Changing next-hop weights leads to change in bucket allocation::
# ip nexthop replace id 10 group 1,3/2 type resilient
This can be confirmed by looking at individual buckets::
# ip nexthop bucket show id 10
id 10 index 0 idle_time 5.59 nhid 1
id 10 index 1 idle_time 5.59 nhid 1
id 10 index 2 idle_time 8.74 nhid 2
id 10 index 3 idle_time 8.74 nhid 2
id 10 index 4 idle_time 8.74 nhid 1
id 10 index 5 idle_time 8.74 nhid 1
id 10 index 6 idle_time 8.74 nhid 1
id 10 index 7 idle_time 8.74 nhid 1
Note the two buckets that have a shorter idle time. Those are the ones that
were migrated after the next-hop replace command to satisfy the new demand
that next hop 1 be given 6 buckets instead of 4.
Netdevsim
---------
The netdevsim driver implements a mock offload of resilient groups, and
exposes debugfs interface that allows marking individual buckets as busy.
For example, the following will mark bucket 23 in next-hop group 10 as
active::
# echo 10 23 > /sys/kernel/debug/netdevsim/netdevsim10/fib/nexthop_bucket_activity
In addition, another debugfs interface can be used to configure that the
next attempt to migrate a bucket should fail::
# echo 1 > /sys/kernel/debug/netdevsim/netdevsim10/fib/fail_nexthop_bucket_replace
Besides serving as an example, the interfaces that netdevsim exposes are
useful in automated testing, and
``tools/testing/selftests/drivers/net/netdevsim/nexthop.sh`` makes use of
them to test the algorithm.

172
Documentation/networking/nf_flowtable.rst
View File

@ -4,35 +4,38 @@
Netfilter's flowtable infrastructure
====================================
This documentation describes the software flowtable infrastructure available in
Netfilter since Linux kernel 4.16.
This documentation describes the Netfilter flowtable infrastructure which allows
you to define a fastpath through the flowtable datapath. This infrastructure
also provides hardware offload support. The flowtable supports for the layer 3
IPv4 and IPv6 and the layer 4 TCP and UDP protocols.
Overview
--------
Initial packets follow the classic forwarding path, once the flow enters the
established state according to the conntrack semantics (ie. we have seen traffic
in both directions), then you can decide to offload the flow to the flowtable
from the forward chain via the 'flow offload' action available in nftables.
Once the first packet of the flow successfully goes through the IP forwarding
path, from the second packet on, you might decide to offload the flow to the
flowtable through your ruleset. The flowtable infrastructure provides a rule
action that allows you to specify when to add a flow to the flowtable.
Packets that find an entry in the flowtable (ie. flowtable hit) are sent to the
output netdevice via neigh_xmit(), hence, they bypass the classic forwarding
path (the visible effect is that you do not see these packets from any of the
netfilter hooks coming after the ingress). In case of flowtable miss, the packet
follows the classic forward path.
A packet that finds a matching entry in the flowtable (ie. flowtable hit) is
transmitted to the output netdevice via neigh_xmit(), hence, packets bypass the
classic IP forwarding path (the visible effect is that you do not see these
packets from any of the Netfilter hooks coming after ingress). In case that
there is no matching entry in the flowtable (ie. flowtable miss), the packet
follows the classic IP forwarding path.
The flowtable uses a resizable hashtable, lookups are based on the following
7-tuple selectors: source, destination, layer 3 and layer 4 protocols, source
and destination ports and the input interface (useful in case there are several
conntrack zones in place).
The flowtable uses a resizable hashtable. Lookups are based on the following
n-tuple selectors: layer 2 protocol encapsulation (VLAN and PPPoE), layer 3
source and destination, layer 4 source and destination ports and the input
interface (useful in case there are several conntrack zones in place).
Flowtables are populated via the 'flow offload' nftables action, so the user can
selectively specify what flows are placed into the flow table. Hence, packets
follow the classic forwarding path unless the user explicitly instruct packets
to use this new alternative forwarding path via nftables policy.
The 'flow add' action allows you to populate the flowtable, the user selectively
specifies what flows are placed into the flowtable. Hence, packets follow the
classic IP forwarding path unless the user explicitly instruct flows to use this
new alternative forwarding path via policy.
This is represented in Fig.1, which describes the classic forwarding path
including the Netfilter hooks and the flowtable fastpath bypass.
The flowtable datapath is represented in Fig.1, which describes the classic IP
forwarding path including the Netfilter hooks and the flowtable fastpath bypass.
::
@ -67,11 +70,13 @@ including the Netfilter hooks and the flowtable fastpath bypass.
Fig.1 Netfilter hooks and flowtable interactions
The flowtable entry also stores the NAT configuration, so all packets are
mangled according to the NAT policy that matches the initial packets that went
through the classic forwarding path. The TTL is decremented before calling
neigh_xmit(). Fragmented traffic is passed up to follow the classic forwarding
path given that the transport selectors are missing, therefore flowtable lookup
is not possible.
mangled according to the NAT policy that is specified from the classic IP
forwarding path. The TTL is decremented before calling neigh_xmit(). Fragmented
traffic is passed up to follow the classic IP forwarding path given that the
transport header is missing, in this case, flowtable lookups are not possible.
TCP RST and FIN packets are also passed up to the classic IP forwarding path to
release the flow gracefully. Packets that exceed the MTU are also passed up to
the classic forwarding path to report packet-too-big ICMP errors to the sender.
Example configuration
---------------------
@ -85,7 +90,7 @@ flowtable and add one rule to your forward chain::
}
chain y {
type filter hook forward priority 0; policy accept;
ip protocol tcp flow offload @f
ip protocol tcp flow add @f
counter packets 0 bytes 0
}
}
@ -103,6 +108,119 @@ flow is offloaded, you will observe that the counter rule in the example above
does not get updated for the packets that are being forwarded through the
forwarding bypass.
You can identify offloaded flows through the [OFFLOAD] tag when listing your
connection tracking table.
::
# conntrack -L
tcp 6 src=10.141.10.2 dst=192.168.10.2 sport=52728 dport=5201 src=192.168.10.2 dst=192.168.10.1 sport=5201 dport=52728 [OFFLOAD] mark=0 use=2
Layer 2 encapsulation
---------------------
Since Linux kernel 5.13, the flowtable infrastructure discovers the real
netdevice behind VLAN and PPPoE netdevices. The flowtable software datapath
parses the VLAN and PPPoE layer 2 headers to extract the ethertype and the
VLAN ID / PPPoE session ID which are used for the flowtable lookups. The
flowtable datapath also deals with layer 2 decapsulation.
You do not need to add the PPPoE and the VLAN devices to your flowtable,
instead the real device is sufficient for the flowtable to track your flows.
Bridge and IP forwarding
------------------------
Since Linux kernel 5.13, you can add bridge ports to the flowtable. The
flowtable infrastructure discovers the topology behind the bridge device. This
allows the flowtable to define a fastpath bypass between the bridge ports
(represented as eth1 and eth2 in the example figure below) and the gateway
device (represented as eth0) in your switch/router.
::
fastpath bypass
.-------------------------.
/ \
| IP forwarding |
| / \ \/
| br0 eth0 ..... eth0
. / \ *host B*
-> eth1 eth2
. *switch/router*
.
.
eth0
*host A*
The flowtable infrastructure also supports for bridge VLAN filtering actions
such as PVID and untagged. You can also stack a classic VLAN device on top of
your bridge port.
If you would like that your flowtable defines a fastpath between your bridge
ports and your IP forwarding path, you have to add your bridge ports (as
represented by the real netdevice) to your flowtable definition.
Counters
--------
The flowtable can synchronize packet and byte counters with the existing
connection tracking entry by specifying the counter statement in your flowtable
definition, e.g.
::
table inet x {
flowtable f {
hook ingress priority 0; devices = { eth0, eth1 };
counter
}
}
Counter support is available since Linux kernel 5.7.
Hardware offload
----------------
If your network device provides hardware offload support, you can turn it on by
means of the 'offload' flag in your flowtable definition, e.g.
::
table inet x {
flowtable f {
hook ingress priority 0; devices = { eth0, eth1 };
flags offload;
}
}
There is a workqueue that adds the flows to the hardware. Note that a few
packets might still run over the flowtable software path until the workqueue has
a chance to offload the flow to the network device.
You can identify hardware offloaded flows through the [HW_OFFLOAD] tag when
listing your connection tracking table. Please, note that the [OFFLOAD] tag
refers to the software offload mode, so there is a distinction between [OFFLOAD]
which refers to the software flowtable fastpath and [HW_OFFLOAD] which refers
to the hardware offload datapath being used by the flow.
The flowtable hardware offload infrastructure also supports for the DSA
(Distributed Switch Architecture).
Limitations
-----------
The flowtable behaves like a cache. The flowtable entries might get stale if
either the destination MAC address or the egress netdevice that is used for
transmission changes.
This might be a problem if:
- You run the flowtable in software mode and you combine bridge and IP
forwarding in your setup.
- Hardware offload is enabled.
More reading
------------

4
Documentation/networking/phy.rst
View File

@ -80,8 +80,8 @@ values of phy_interface_t must be understood from the perspective of the PHY
device itself, leading to the following:
* PHY_INTERFACE_MODE_RGMII: the PHY is not responsible for inserting any
internal delay by itself, it assumes that either the Ethernet MAC (if capable
or the PCB traces) insert the correct 1.5-2ns delay
internal delay by itself, it assumes that either the Ethernet MAC (if capable)
or the PCB traces insert the correct 1.5-2ns delay
* PHY_INTERFACE_MODE_RGMII_TXID: the PHY should insert an internal delay
for the transmit data lines (TXD[3:0]) processed by the PHY device

46
Documentation/networking/statistics.rst
View File

@ -44,8 +44,27 @@ If `-s` is specified once the detailed errors won't be shown.
Protocol-specific statistics
----------------------------
Some of the interfaces used for configuring devices are also able
to report related statistics. For example ethtool interface used
Protocol-specific statistics are exposed via relevant interfaces,
the same interfaces as are used to configure them.
ethtool
~~~~~~~
Ethtool exposes common low-level statistics.
All the standard statistics are expected to be maintained
by the device, not the driver (as opposed to driver-defined stats
described in the next section which mix software and hardware stats).
For devices which contain unmanaged
switches (e.g. legacy SR-IOV or multi-host NICs) the events counted
may not pertain exclusively to the packets destined to
the local host interface. In other words the events may
be counted at the network port (MAC/PHY blocks) without separation
for different host side (PCIe) devices. Such ambiguity must not
be present when internal switch is managed by Linux (so called
switchdev mode for NICs).
Standard ethtool statistics can be accessed via the interfaces used
for configuration. For example ethtool interface used
to configure pause frames can report corresponding hardware counters::
$ ethtool --include-statistics -a eth0
@ -57,6 +76,27 @@ to configure pause frames can report corresponding hardware counters::
tx_pause_frames: 1
rx_pause_frames: 1
General Ethernet statistics not associated with any particular
functionality are exposed via ``ethtool -S $ifc`` by specifying
the ``--groups`` parameter::
$ ethtool -S eth0 --groups eth-phy eth-mac eth-ctrl rmon
Stats for eth0:
eth-phy-SymbolErrorDuringCarrier: 0
eth-mac-FramesTransmittedOK: 1
eth-mac-FrameTooLongErrors: 1
eth-ctrl-MACControlFramesTransmitted: 1
eth-ctrl-MACControlFramesReceived: 0
eth-ctrl-UnsupportedOpcodesReceived: 1
rmon-etherStatsUndersizePkts: 1
rmon-etherStatsJabbers: 0
rmon-rx-etherStatsPkts64Octets: 1
rmon-rx-etherStatsPkts65to127Octets: 0
rmon-rx-etherStatsPkts128to255Octets: 0
rmon-tx-etherStatsPkts64Octets: 2
rmon-tx-etherStatsPkts65to127Octets: 3
rmon-tx-etherStatsPkts128to255Octets: 0
Driver-defined statistics
-------------------------
@ -130,6 +170,7 @@ the `ETHTOOL_FLAG_STATS` flag in `ETHTOOL_A_HEADER_FLAGS`. Currently
statistics are supported in the following commands:
- `ETHTOOL_MSG_PAUSE_GET`
- `ETHTOOL_MSG_FEC_GET`
debugfs
-------
@ -176,3 +217,4 @@ translated to netlink attributes when dumped. Drivers must not overwrite
the statistics they don't report with 0.
- ethtool_pause_stats()
- ethtool_fec_stats()

194
Documentation/networking/switchdev.rst
View File

@ -181,18 +181,41 @@ To offloading L2 bridging, the switchdev driver/device should support:
Static FDB Entries
^^^^^^^^^^^^^^^^^^
The switchdev driver should implement ndo_fdb_add, ndo_fdb_del and ndo_fdb_dump
to support static FDB entries installed to the device. Static bridge FDB
entries are installed, for example, using iproute2 bridge cmd::
A driver which implements the ``ndo_fdb_add``, ``ndo_fdb_del`` and
``ndo_fdb_dump`` operations is able to support the command below, which adds a
static bridge FDB entry::
bridge fdb add ADDR dev DEV [vlan VID] [self]
bridge fdb add dev DEV ADDRESS [vlan VID] [self] static
The driver should use the helper switchdev_port_fdb_xxx ops for ndo_fdb_xxx
ops, and handle add/delete/dump of SWITCHDEV_OBJ_ID_PORT_FDB object using
switchdev_port_obj_xxx ops.
(the "static" keyword is non-optional: if not specified, the entry defaults to
being "local", which means that it should not be forwarded)
XXX: what should be done if offloading this rule to hardware fails (for
example, due to full capacity in hardware tables) ?
The "self" keyword (optional because it is implicit) has the role of
instructing the kernel to fulfill the operation through the ``ndo_fdb_add``
implementation of the ``DEV`` device itself. If ``DEV`` is a bridge port, this
will bypass the bridge and therefore leave the software database out of sync
with the hardware one.
To avoid this, the "master" keyword can be used::
bridge fdb add dev DEV ADDRESS [vlan VID] master static
The above command instructs the kernel to search for a master interface of
``DEV`` and fulfill the operation through the ``ndo_fdb_add`` method of that.
This time, the bridge generates a ``SWITCHDEV_FDB_ADD_TO_DEVICE`` notification
which the port driver can handle and use it to program its hardware table. This
way, the software and the hardware database will both contain this static FDB
entry.
Note: for new switchdev drivers that offload the Linux bridge, implementing the
``ndo_fdb_add`` and ``ndo_fdb_del`` bridge bypass methods is strongly
discouraged: all static FDB entries should be added on a bridge port using the
"master" flag. The ``ndo_fdb_dump`` is an exception and can be implemented to
visualize the hardware tables, if the device does not have an interrupt for
notifying the operating system of newly learned/forgotten dynamic FDB
addresses. In that case, the hardware FDB might end up having entries that the
software FDB does not, and implementing ``ndo_fdb_dump`` is the only way to see
them.
Note: by default, the bridge does not filter on VLAN and only bridges untagged
traffic. To enable VLAN support, turn on VLAN filtering::
@ -385,3 +408,156 @@ The driver can monitor for updates to arp_tbl using the netevent notifier
NETEVENT_NEIGH_UPDATE. The device can be programmed with resolved nexthops
for the routes as arp_tbl updates. The driver implements ndo_neigh_destroy
to know when arp_tbl neighbor entries are purged from the port.
Device driver expected behavior
-------------------------------
Below is a set of defined behavior that switchdev enabled network devices must
adhere to.
Configuration-less state
^^^^^^^^^^^^^^^^^^^^^^^^
Upon driver bring up, the network devices must be fully operational, and the
backing driver must configure the network device such that it is possible to
send and receive traffic to this network device and it is properly separated
from other network devices/ports (e.g.: as is frequent with a switch ASIC). How
this is achieved is heavily hardware dependent, but a simple solution can be to
use per-port VLAN identifiers unless a better mechanism is available
(proprietary metadata for each network port for instance).
The network device must be capable of running a full IP protocol stack
including multicast, DHCP, IPv4/6, etc. If necessary, it should program the
appropriate filters for VLAN, multicast, unicast etc. The underlying device
driver must effectively be configured in a similar fashion to what it would do
when IGMP snooping is enabled for IP multicast over these switchdev network
devices and unsolicited multicast must be filtered as early as possible in
the hardware.
When configuring VLANs on top of the network device, all VLANs must be working,
irrespective of the state of other network devices (e.g.: other ports being part
of a VLAN-aware bridge doing ingress VID checking). See below for details.
If the device implements e.g.: VLAN filtering, putting the interface in
promiscuous mode should allow the reception of all VLAN tags (including those
not present in the filter(s)).
Bridged switch ports
^^^^^^^^^^^^^^^^^^^^
When a switchdev enabled network device is added as a bridge member, it should
not disrupt any functionality of non-bridged network devices and they
should continue to behave as normal network devices. Depending on the bridge
configuration knobs below, the expected behavior is documented.
Bridge VLAN filtering
^^^^^^^^^^^^^^^^^^^^^
The Linux bridge allows the configuration of a VLAN filtering mode (statically,
at device creation time, and dynamically, during run time) which must be
observed by the underlying switchdev network device/hardware:
- with VLAN filtering turned off: the bridge is strictly VLAN unaware and its
data path will process all Ethernet frames as if they are VLAN-untagged.
The bridge VLAN database can still be modified, but the modifications should
have no effect while VLAN filtering is turned off. Frames ingressing the
device with a VID that is not programmed into the bridge/switch's VLAN table
must be forwarded and may be processed using a VLAN device (see below).
- with VLAN filtering turned on: the bridge is VLAN-aware and frames ingressing
the device with a VID that is not programmed into the bridges/switch's VLAN
table must be dropped (strict VID checking).
When there is a VLAN device (e.g: sw0p1.100) configured on top of a switchdev
network device which is a bridge port member, the behavior of the software
network stack must be preserved, or the configuration must be refused if that
is not possible.
- with VLAN filtering turned off, the bridge will process all ingress traffic
for the port, except for the traffic tagged with a VLAN ID destined for a
VLAN upper. The VLAN upper interface (which consumes the VLAN tag) can even
be added to a second bridge, which includes other switch ports or software
interfaces. Some approaches to ensure that the forwarding domain for traffic
belonging to the VLAN upper interfaces are managed properly:
* If forwarding destinations can be managed per VLAN, the hardware could be
configured to map all traffic, except the packets tagged with a VID
belonging to a VLAN upper interface, to an internal VID corresponding to
untagged packets. This internal VID spans all ports of the VLAN-unaware
bridge. The VID corresponding to the VLAN upper interface spans the
physical port of that VLAN interface, as well as the other ports that
might be bridged with it.
* Treat bridge ports with VLAN upper interfaces as standalone, and let
forwarding be handled in the software data path.
- with VLAN filtering turned on, these VLAN devices can be created as long as
the bridge does not have an existing VLAN entry with the same VID on any
bridge port. These VLAN devices cannot be enslaved into the bridge since they
duplicate functionality/use case with the bridge's VLAN data path processing.
Non-bridged network ports of the same switch fabric must not be disturbed in any
way by the enabling of VLAN filtering on the bridge device(s). If the VLAN
filtering setting is global to the entire chip, then the standalone ports
should indicate to the network stack that VLAN filtering is required by setting
'rx-vlan-filter: on [fixed]' in the ethtool features.
Because VLAN filtering can be turned on/off at runtime, the switchdev driver
must be able to reconfigure the underlying hardware on the fly to honor the
toggling of that option and behave appropriately. If that is not possible, the
switchdev driver can also refuse to support dynamic toggling of the VLAN
filtering knob at runtime and require a destruction of the bridge device(s) and
creation of new bridge device(s) with a different VLAN filtering value to
ensure VLAN awareness is pushed down to the hardware.
Even when VLAN filtering in the bridge is turned off, the underlying switch
hardware and driver may still configure itself in a VLAN-aware mode provided
that the behavior described above is observed.
The VLAN protocol of the bridge plays a role in deciding whether a packet is
treated as tagged or not: a bridge using the 802.1ad protocol must treat both
VLAN-untagged packets, as well as packets tagged with 802.1Q headers, as
untagged.
The 802.1p (VID 0) tagged packets must be treated in the same way by the device
as untagged packets, since the bridge device does not allow the manipulation of
VID 0 in its database.
When the bridge has VLAN filtering enabled and a PVID is not configured on the
ingress port, untagged and 802.1p tagged packets must be dropped. When the bridge
has VLAN filtering enabled and a PVID exists on the ingress port, untagged and
priority-tagged packets must be accepted and forwarded according to the
bridge's port membership of the PVID VLAN. When the bridge has VLAN filtering
disabled, the presence/lack of a PVID should not influence the packet
forwarding decision.
Bridge IGMP snooping
^^^^^^^^^^^^^^^^^^^^
The Linux bridge allows the configuration of IGMP snooping (statically, at
interface creation time, or dynamically, during runtime) which must be observed
by the underlying switchdev network device/hardware in the following way:
- when IGMP snooping is turned off, multicast traffic must be flooded to all
ports within the same bridge that have mcast_flood=true. The CPU/management
port should ideally not be flooded (unless the ingress interface has
IFF_ALLMULTI or IFF_PROMISC) and continue to learn multicast traffic through
the network stack notifications. If the hardware is not capable of doing that
then the CPU/management port must also be flooded and multicast filtering
happens in software.
- when IGMP snooping is turned on, multicast traffic must selectively flow
to the appropriate network ports (including CPU/management port). Flooding of
unknown multicast should be only towards the ports connected to a multicast
router (the local device may also act as a multicast router).
The switch must adhere to RFC 4541 and flood multicast traffic accordingly
since that is what the Linux bridge implementation does.
Because IGMP snooping can be turned on/off at runtime, the switchdev driver
must be able to reconfigure the underlying hardware on the fly to honor the
toggling of that option and behave appropriately.
A switchdev driver can also refuse to support dynamic toggling of the multicast
snooping knob at runtime and require the destruction of the bridge device(s)
and creation of a new bridge device(s) with a different multicast snooping
value.

59
Documentation/networking/timestamping.rst
View File

@ -630,30 +630,45 @@ hardware timestamping on it. This is because the SO_TIMESTAMPING API does not
allow the delivery of multiple hardware timestamps for the same packet, so
anybody else except for the DSA switch port must be prevented from doing so.
In code, DSA provides for most of the infrastructure for timestamping already,
in generic code: a BPF classifier (``ptp_classify_raw``) is used to identify
PTP event messages (any other packets, including PTP general messages, are not
timestamped), and provides two hooks to drivers:
In the generic layer, DSA provides the following infrastructure for PTP
timestamping:
- ``.port_txtstamp()``: The driver is passed a clone of the timestampable skb
to be transmitted, before actually transmitting it. Typically, a switch will
have a PTP TX timestamp register (or sometimes a FIFO) where the timestamp
becomes available. There may be an IRQ that is raised upon this timestamp's
availability, or the driver might have to poll after invoking
``dev_queue_xmit()`` towards the host interface. Either way, in the
``.port_txtstamp()`` method, the driver only needs to save the clone for
later use (when the timestamp becomes available). Each skb is annotated with
a pointer to its clone, in ``DSA_SKB_CB(skb)->clone``, to ease the driver's
job of keeping track of which clone belongs to which skb.
- ``.port_txtstamp()``: a hook called prior to the transmission of
packets with a hardware TX timestamping request from user space.
This is required for two-step timestamping, since the hardware
timestamp becomes available after the actual MAC transmission, so the
driver must be prepared to correlate the timestamp with the original
packet so that it can re-enqueue the packet back into the socket's
error queue. To save the packet for when the timestamp becomes
available, the driver can call ``skb_clone_sk`` , save the clone pointer
in skb->cb and enqueue a tx skb queue. Typically, a switch will have a
PTP TX timestamp register (or sometimes a FIFO) where the timestamp
becomes available. In case of a FIFO, the hardware might store
key-value pairs of PTP sequence ID/message type/domain number and the
actual timestamp. To perform the correlation correctly between the
packets in a queue waiting for timestamping and the actual timestamps,
drivers can use a BPF classifier (``ptp_classify_raw``) to identify
the PTP transport type, and ``ptp_parse_header`` to interpret the PTP
header fields. There may be an IRQ that is raised upon this
timestamp's availability, or the driver might have to poll after
invoking ``dev_queue_xmit()`` towards the host interface.
One-step TX timestamping do not require packet cloning, since there is
no follow-up message required by the PTP protocol (because the
TX timestamp is embedded into the packet by the MAC), and therefore
user space does not expect the packet annotated with the TX timestamp
to be re-enqueued into its socket's error queue.
- ``.port_rxtstamp()``: The original (and only) timestampable skb is provided
to the driver, for it to annotate it with a timestamp, if that is immediately
available, or defer to later. On reception, timestamps might either be
available in-band (through metadata in the DSA header, or attached in other
ways to the packet), or out-of-band (through another RX timestamping FIFO).
Deferral on RX is typically necessary when retrieving the timestamp needs a
sleepable context. In that case, it is the responsibility of the DSA driver
to call ``netif_rx_ni()`` on the freshly timestamped skb.
- ``.port_rxtstamp()``: On RX, the BPF classifier is run by DSA to
identify PTP event messages (any other packets, including PTP general
messages, are not timestamped). The original (and only) timestampable
skb is provided to the driver, for it to annotate it with a timestamp,
if that is immediately available, or defer to later. On reception,
timestamps might either be available in-band (through metadata in the
DSA header, or attached in other ways to the packet), or out-of-band
(through another RX timestamping FIFO). Deferral on RX is typically
necessary when retrieving the timestamp needs a sleepable context. In
that case, it is the responsibility of the DSA driver to call
``netif_rx_ni()`` on the freshly timestamped skb.
3.2.2 Ethernet PHYs
^^^^^^^^^^^^^^^^^^^

63
Documentation/networking/x25-iface.rst
View File

@ -70,60 +70,13 @@ First Byte = 0x03 (X25_IFACE_PARAMS)
LAPB parameters. To be defined.
Requirements for the device driver
----------------------------------
Possible Problems
=================
Packets should not be reordered or dropped when delivering between the
Packet Layer and the device driver.
(Henner Eisen, 2000-10-28)
The X.25 packet layer protocol depends on a reliable datalink service.
The LAPB protocol provides such reliable service. But this reliability
is not preserved by the Linux network device driver interface:
- With Linux 2.4.x (and above) SMP kernels, packet ordering is not
preserved. Even if a device driver calls netif_rx(skb1) and later
netif_rx(skb2), skb2 might be delivered to the network layer
earlier that skb1.
- Data passed upstream by means of netif_rx() might be dropped by the
kernel if the backlog queue is congested.
The X.25 packet layer protocol will detect this and reset the virtual
call in question. But many upper layer protocols are not designed to
handle such N-Reset events gracefully. And frequent N-Reset events
will always degrade performance.
Thus, driver authors should make netif_rx() as reliable as possible:
SMP re-ordering will not occur if the driver's interrupt handler is
always executed on the same CPU. Thus,
- Driver authors should use irq affinity for the interrupt handler.
The probability of packet loss due to backlog congestion can be
reduced by the following measures or a combination thereof:
(1) Drivers for kernel versions 2.4.x and above should always check the
return value of netif_rx(). If it returns NET_RX_DROP, the
driver's LAPB protocol must not confirm reception of the frame
to the peer.
This will reliably suppress packet loss. The LAPB protocol will
automatically cause the peer to re-transmit the dropped packet
later.
The lapb module interface was modified to support this. Its
data_indication() method should now transparently pass the
netif_rx() return value to the (lapb module) caller.
(2) Drivers for kernel versions 2.2.x should always check the global
variable netdev_dropping when a new frame is received. The driver
should only call netif_rx() if netdev_dropping is zero. Otherwise
the driver should not confirm delivery of the frame and drop it.
Alternatively, the driver can queue the frame internally and call
netif_rx() later when netif_dropping is 0 again. In that case, delivery
confirmation should also be deferred such that the internal queue
cannot grow to much.
This will not reliably avoid packet loss, but the probability
of packet loss in netif_rx() path will be significantly reduced.
(3) Additionally, driver authors might consider to support
CONFIG_NET_HW_FLOWCONTROL. This allows the driver to be woken up
when a previously congested backlog queue becomes empty again.
The driver could uses this for flow-controlling the peer by means
of the LAPB protocol's flow-control service.
To avoid packets from being reordered or dropped when delivering from
the device driver to the Packet Layer, the device driver should not
call "netif_rx" to deliver the received packets. Instead, it should
call "netif_receive_skb_core" from softirq context to deliver them.

17
Documentation/userspace-api/ebpf/index.rst Normal file
View File

@ -0,0 +1,17 @@
.. SPDX-License-Identifier: GPL-2.0
eBPF Userspace API
==================
eBPF is a kernel mechanism to provide a sandboxed runtime environment in the
Linux kernel for runtime extension and instrumentation without changing kernel
source code or loading kernel modules. eBPF programs can be attached to various
kernel subsystems, including networking, tracing and Linux security modules
(LSM).
For internal kernel documentation on eBPF, see Documentation/bpf/index.rst.
.. toctree::
:maxdepth: 1
syscall

24
Documentation/userspace-api/ebpf/syscall.rst Normal file
View File

@ -0,0 +1,24 @@
.. SPDX-License-Identifier: GPL-2.0
eBPF Syscall
------------
:Authors: - Alexei Starovoitov <ast@kernel.org>
- Joe Stringer <joe@wand.net.nz>
- Michael Kerrisk <mtk.manpages@gmail.com>
The primary info for the bpf syscall is available in the `man-pages`_
for `bpf(2)`_.
bpf() subcommand reference
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. kernel-doc:: include/uapi/linux/bpf.h
:doc: eBPF Syscall Preamble
.. kernel-doc:: include/uapi/linux/bpf.h
:doc: eBPF Syscall Commands
.. Links:
.. _man-pages: https://www.kernel.org/doc/man-pages/
.. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html

1
Documentation/userspace-api/index.rst
View File

@ -21,6 +21,7 @@ place where this information is gathered.
unshare
spec_ctrl
accelerators/ocxl
ebpf/index
ioctl/index
iommu
media/index

31
MAINTAINERS
View File

@ -1533,6 +1533,7 @@ F: Documentation/devicetree/bindings/dma/owl-dma.yaml
F: Documentation/devicetree/bindings/i2c/i2c-owl.yaml
F: Documentation/devicetree/bindings/interrupt-controller/actions,owl-sirq.yaml
F: Documentation/devicetree/bindings/mmc/owl-mmc.yaml
F: Documentation/devicetree/bindings/net/actions,owl-emac.yaml
F: Documentation/devicetree/bindings/pinctrl/actions,*
F: Documentation/devicetree/bindings/power/actions,owl-sps.txt
F: Documentation/devicetree/bindings/timer/actions,owl-timer.txt
@ -1545,6 +1546,7 @@ F: drivers/dma/owl-dma.c
F: drivers/i2c/busses/i2c-owl.c
F: drivers/irqchip/irq-owl-sirq.c
F: drivers/mmc/host/owl-mmc.c
F: drivers/net/ethernet/actions/
F: drivers/pinctrl/actions/*
F: drivers/soc/actions/
F: include/dt-bindings/power/owl-*
@ -3285,6 +3287,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
F: Documentation/bpf/
F: Documentation/networking/filter.rst
F: Documentation/userspace-api/ebpf/
F: arch/*/net/*
F: include/linux/bpf*
F: include/linux/filter.h
@ -3299,6 +3302,7 @@ F: net/core/filter.c
F: net/sched/act_bpf.c
F: net/sched/cls_bpf.c
F: samples/bpf/
F: scripts/bpf_doc.py
F: tools/bpf/
F: tools/lib/bpf/
F: tools/testing/selftests/bpf/
@ -5555,11 +5559,11 @@ F: drivers/net/ethernet/freescale/dpaa2/dpmac*
F: drivers/net/ethernet/freescale/dpaa2/dpni*
DPAA2 ETHERNET SWITCH DRIVER
M: Ioana Radulescu <ruxandra.radulescu@nxp.com>
M: Ioana Ciornei <ioana.ciornei@nxp.com>
L: linux-kernel@vger.kernel.org
L: netdev@vger.kernel.org
S: Maintained
F: drivers/staging/fsl-dpaa2/ethsw
F: drivers/net/ethernet/freescale/dpaa2/dpaa2-switch*
F: drivers/net/ethernet/freescale/dpaa2/dpsw*
DPT_I2O SCSI RAID DRIVER
M: Adaptec OEM Raid Solutions <aacraid@microsemi.com>
@ -8370,11 +8374,12 @@ S: Maintained
T: git git://linuxtv.org/media_tree.git
F: drivers/media/i2c/hi556.c
Hyper-V CORE AND DRIVERS
Hyper-V/Azure CORE AND DRIVERS
M: "K. Y. Srinivasan" <kys@microsoft.com>
M: Haiyang Zhang <haiyangz@microsoft.com>
M: Stephen Hemminger <sthemmin@microsoft.com>
M: Wei Liu <wei.liu@kernel.org>
M: Dexuan Cui <decui@microsoft.com>
L: linux-hyperv@vger.kernel.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
@ -8391,6 +8396,7 @@ F: drivers/hid/hid-hyperv.c
F: drivers/hv/
F: drivers/input/serio/hyperv-keyboard.c
F: drivers/iommu/hyperv-iommu.c
F: drivers/net/ethernet/microsoft/
F: drivers/net/hyperv/
F: drivers/pci/controller/pci-hyperv-intf.c
F: drivers/pci/controller/pci-hyperv.c
@ -8633,7 +8639,6 @@ IBM Power SRIOV Virtual NIC Device Driver
M: Dany Madden <drt@linux.ibm.com>
M: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
R: Thomas Falcon <tlfalcon@linux.ibm.com>
R: Lijun Pan <lijunp213@gmail.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/ibm/ibmvnic.*
@ -10858,6 +10863,7 @@ F: include/linux/mv643xx.h
MARVELL MV88X3310 PHY DRIVER
M: Russell King <linux@armlinux.org.uk>
M: Marek Behun <marek.behun@nic.cz>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/phy/marvell10g.c
@ -11080,7 +11086,7 @@ T: git git://linuxtv.org/media_tree.git
F: drivers/media/radio/radio-maxiradio*
MCAN MMIO DEVICE DRIVER
M: Pankaj Sharma <pankj.sharma@samsung.com>
M: Chandrasekar Ramakrishnan <rcsekar@samsung.com>
L: linux-can@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
@ -12749,6 +12755,7 @@ W: https://github.com/multipath-tcp/mptcp_net-next/wiki
B: https://github.com/multipath-tcp/mptcp_net-next/issues
F: Documentation/networking/mptcp-sysctl.rst
F: include/net/mptcp.h
F: include/trace/events/mptcp.h
F: include/uapi/linux/mptcp.h
F: net/mptcp/
F: tools/testing/selftests/net/mptcp/
@ -13033,6 +13040,12 @@ F: drivers/nvmem/
F: include/linux/nvmem-consumer.h
F: include/linux/nvmem-provider.h
NXP C45 TJA11XX PHY DRIVER
M: Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/phy/nxp-c45-tja11xx.c
NXP FSPI DRIVER
M: Ashish Kumar <ashish.kumar@nxp.com>
R: Yogesh Gaur <yogeshgaur.83@gmail.com>
@ -18222,12 +18235,6 @@ L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Odd Fixes
F: sound/soc/codecs/tas571x*
TI TCAN4X5X DEVICE DRIVER
L: linux-can@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/can/tcan4x5x.txt
F: drivers/net/can/m_can/tcan4x5x*
TI TRF7970A NFC DRIVER
M: Mark Greer <mgreer@animalcreek.com>
L: linux-wireless@vger.kernel.org

2
arch/arm/boot/dts/uniphier-pxs2.dtsi
View File

@ -583,7 +583,7 @@ eth: ethernet@65000000 {
clocks = <&sys_clk 6>;
reset-names = "ether";
resets = <&sys_rst 6>;
phy-mode = "rgmii";
phy-mode = "rgmii-id";
local-mac-address = [00 00 00 00 00 00];
socionext,syscon-phy-mode = <&soc_glue 0>;

3
arch/arm/mach-mvebu/kirkwood.c
View File

@ -84,6 +84,7 @@ static void __init kirkwood_dt_eth_fixup(void)
struct device_node *pnp = of_get_parent(np);
struct clk *clk;
struct property *pmac;
u8 tmpmac[ETH_ALEN];
void __iomem *io;
u8 *macaddr;
u32 reg;
@ -93,7 +94,7 @@ static void __init kirkwood_dt_eth_fixup(void)
/* skip disabled nodes or nodes with valid MAC address*/
if (!of_device_is_available(pnp) ||
!IS_ERR(of_get_mac_address(np)))
!of_get_mac_address(np, tmpmac))
goto eth_fixup_skip;
clk = of_clk_get(pnp, 0);

6
arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
View File

@ -1118,6 +1118,12 @@ rcec@1f,0 {
};
};
/* Integrated Endpoint Register Block */
ierb@1f0800000 {
compatible = "fsl,ls1028a-enetc-ierb";
reg = <0x01 0xf0800000 0x0 0x10000>;
};
rcpm: power-controller@1e34040 {
compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x1c>;

4
arch/arm64/boot/dts/rockchip/rk3328.dtsi
View File

@ -916,8 +916,8 @@ gmac2phy: ethernet@ff550000 {
"mac_clk_tx", "clk_mac_ref",
"aclk_mac", "pclk_mac",
"clk_macphy";
resets = <&cru SRST_GMAC2PHY_A>, <&cru SRST_MACPHY>;
reset-names = "stmmaceth", "mac-phy";
resets = <&cru SRST_GMAC2PHY_A>;
reset-names = "stmmaceth";
phy-mode = "rmii";
phy-handle = <&phy>;
snps,txpbl = <0x4>;

2
arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
View File

@ -734,7 +734,7 @@ eth: ethernet@65000000 {
clocks = <&sys_clk 6>;
reset-names = "ether";
resets = <&sys_rst 6>;
phy-mode = "rgmii";
phy-mode = "rgmii-id";
local-mac-address = [00 00 00 00 00 00];
socionext,syscon-phy-mode = <&soc_glue 0>;

4
arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
View File

@ -564,7 +564,7 @@ eth0: ethernet@65000000 {
clocks = <&sys_clk 6>;
reset-names = "ether";
resets = <&sys_rst 6>;
phy-mode = "rgmii";
phy-mode = "rgmii-id";
local-mac-address = [00 00 00 00 00 00];
socionext,syscon-phy-mode = <&soc_glue 0>;
@ -585,7 +585,7 @@ eth1: ethernet@65200000 {
clocks = <&sys_clk 7>;
reset-names = "ether";
resets = <&sys_rst 7>;
phy-mode = "rgmii";
phy-mode = "rgmii-id";
local-mac-address = [00 00 00 00 00 00];
socionext,syscon-phy-mode = <&soc_glue 1>;

25
arch/mips/rb532/devices.c
View File

@ -58,37 +58,27 @@ EXPORT_SYMBOL(get_latch_u5);
static struct resource korina_dev0_res[] = {
{
.name = "korina_regs",
.name = "emac",
.start = ETH0_BASE_ADDR,
.end = ETH0_BASE_ADDR + sizeof(struct eth_regs),
.flags = IORESOURCE_MEM,
}, {
.name = "korina_rx",
.name = "rx",
.start = ETH0_DMA_RX_IRQ,
.end = ETH0_DMA_RX_IRQ,
.flags = IORESOURCE_IRQ
}, {
.name = "korina_tx",
.name = "tx",
.start = ETH0_DMA_TX_IRQ,
.end = ETH0_DMA_TX_IRQ,
.flags = IORESOURCE_IRQ
}, {
.name = "korina_ovr",
.start = ETH0_RX_OVR_IRQ,
.end = ETH0_RX_OVR_IRQ,
.flags = IORESOURCE_IRQ
}, {
.name = "korina_und",
.start = ETH0_TX_UND_IRQ,
.end = ETH0_TX_UND_IRQ,
.flags = IORESOURCE_IRQ
}, {
.name = "korina_dma_rx",
.name = "dma_rx",
.start = ETH0_RX_DMA_ADDR,
.end = ETH0_RX_DMA_ADDR + DMA_CHAN_OFFSET - 1,
.flags = IORESOURCE_MEM,
}, {
.name = "korina_dma_tx",
.name = "dma_tx",
.start = ETH0_TX_DMA_ADDR,
.end = ETH0_TX_DMA_ADDR + DMA_CHAN_OFFSET - 1,
.flags = IORESOURCE_MEM,
@ -105,6 +95,9 @@ static struct platform_device korina_dev0 = {
.name = "korina",
.resource = korina_dev0_res,
.num_resources = ARRAY_SIZE(korina_dev0_res),
.dev = {
.platform_data = &korina_dev0_data.mac,
}
};
static struct resource cf_slot0_res[] = {
@ -299,8 +292,6 @@ static int __init plat_setup_devices(void)
/* set the uart clock to the current cpu frequency */
rb532_uart_res[0].uartclk = idt_cpu_freq;
dev_set_drvdata(&korina_dev0.dev, &korina_dev0_data);
gpiod_add_lookup_table(&cf_slot0_gpio_table);
return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs));
}

4
arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
View File

@ -170,8 +170,6 @@ timer@41100 {
/include/ "pq3-etsec2-0.dtsi"
enet0: ethernet@b0000 {
queue-group@b0000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
interrupts = <26 2 0 0 27 2 0 0 28 2 0 0>;
};
};
@ -179,8 +177,6 @@ queue-group@b0000 {
/include/ "pq3-etsec2-1.dtsi"
enet1: ethernet@b1000 {
queue-group@b1000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
interrupts = <33 2 0 0 34 2 0 0 35 2 0 0>;
};
};

4
arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
View File

@ -190,8 +190,6 @@ sec_jr3: jr@4000 {
/include/ "pq3-etsec2-0.dtsi"
enet0: ethernet@b0000 {
queue-group@b0000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
interrupts = <26 2 0 0 27 2 0 0 28 2 0 0>;
};
};
@ -199,8 +197,6 @@ queue-group@b0000 {
/include/ "pq3-etsec2-1.dtsi"
enet1: ethernet@b1000 {
queue-group@b1000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
interrupts = <33 2 0 0 34 2 0 0 35 2 0 0>;
};
};

4
arch/powerpc/boot/dts/fsl/c293si-post.dtsi
View File

@ -171,8 +171,6 @@ jr@2000{
enet0: ethernet@b0000 {
queue-group@b0000 {
reg = <0x10000 0x1000>;
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
};
};
@ -180,8 +178,6 @@ queue-group@b0000 {
enet1: ethernet@b1000 {
queue-group@b1000 {
reg = <0x11000 0x1000>;
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
};
};

21
arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
View File

@ -172,29 +172,8 @@ sdhc@2e000 {
/include/ "pq3-mpic-timer-B.dtsi"
/include/ "pq3-etsec2-0.dtsi"
enet0: ethernet@b0000 {
queue-group@b0000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
};
};
/include/ "pq3-etsec2-1.dtsi"
enet1: ethernet@b1000 {
queue-group@b1000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
};
};
/include/ "pq3-etsec2-2.dtsi"
enet2: ethernet@b2000 {
queue-group@b2000 {
fsl,rx-bit-map = <0xff>;
fsl,tx-bit-map = <0xff>;
};
};
global-utilities@e0000 {
compatible = "fsl,p1010-guts";

5
arch/powerpc/sysdev/tsi108_dev.c
View File

@ -73,7 +73,6 @@ static int __init tsi108_eth_of_init(void)
struct device_node *phy, *mdio;
hw_info tsi_eth_data;
const unsigned int *phy_id;
const void *mac_addr;
const phandle *ph;
memset(r, 0, sizeof(r));
@ -101,9 +100,7 @@ static int __init tsi108_eth_of_init(void)
goto err;
}
mac_addr = of_get_mac_address(np);
if (!IS_ERR(mac_addr))
ether_addr_copy(tsi_eth_data.mac_addr, mac_addr);
of_get_mac_address(np, tsi_eth_data.mac_addr);
ph = of_get_property(np, "mdio-handle", NULL);
mdio = of_find_node_by_phandle(*ph);

64
arch/s390/net/bpf_jit_comp.c
View File

@ -1209,21 +1209,67 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
*/
case BPF_STX | BPF_ATOMIC | BPF_DW:
case BPF_STX | BPF_ATOMIC | BPF_W:
if (insn->imm != BPF_ADD) {
{
bool is32 = BPF_SIZE(insn->code) == BPF_W;
switch (insn->imm) {
/* {op32|op64} {%w0|%src},%src,off(%dst) */
#define EMIT_ATOMIC(op32, op64) do { \
EMIT6_DISP_LH(0xeb000000, is32 ? (op32) : (op64), \
(insn->imm & BPF_FETCH) ? src_reg : REG_W0, \
src_reg, dst_reg, off); \
if (is32 && (insn->imm & BPF_FETCH)) \
EMIT_ZERO(src_reg); \
} while (0)
case BPF_ADD:
case BPF_ADD | BPF_FETCH:
/* {laal|laalg} */
EMIT_ATOMIC(0x00fa, 0x00ea);
break;
case BPF_AND:
case BPF_AND | BPF_FETCH:
/* {lan|lang} */
EMIT_ATOMIC(0x00f4, 0x00e4);
break;
case BPF_OR:
case BPF_OR | BPF_FETCH:
/* {lao|laog} */
EMIT_ATOMIC(0x00f6, 0x00e6);
break;
case BPF_XOR:
case BPF_XOR | BPF_FETCH:
/* {lax|laxg} */
EMIT_ATOMIC(0x00f7, 0x00e7);
break;
#undef EMIT_ATOMIC
case BPF_XCHG:
/* {ly|lg} %w0,off(%dst) */
EMIT6_DISP_LH(0xe3000000,
is32 ? 0x0058 : 0x0004, REG_W0, REG_0,
dst_reg, off);
/* 0: {csy|csg} %w0,%src,off(%dst) */
EMIT6_DISP_LH(0xeb000000, is32 ? 0x0014 : 0x0030,
REG_W0, src_reg, dst_reg, off);
/* brc 4,0b */
EMIT4_PCREL_RIC(0xa7040000, 4, jit->prg - 6);
/* {llgfr|lgr} %src,%w0 */
EMIT4(is32 ? 0xb9160000 : 0xb9040000, src_reg, REG_W0);
if (is32 && insn_is_zext(&insn[1]))
insn_count = 2;
break;
case BPF_CMPXCHG:
/* 0: {csy|csg} %b0,%src,off(%dst) */
EMIT6_DISP_LH(0xeb000000, is32 ? 0x0014 : 0x0030,
BPF_REG_0, src_reg, dst_reg, off);
break;
default:
pr_err("Unknown atomic operation %02x\n", insn->imm);
return -1;
}
/* *(u32/u64 *)(dst + off) += src
*
* BFW_W: laal %w0,%src,off(%dst)
* BPF_DW: laalg %w0,%src,off(%dst)
*/
EMIT6_DISP_LH(0xeb000000,
BPF_SIZE(insn->code) == BPF_W ? 0x00fa : 0x00ea,
REG_W0, src_reg, dst_reg, off);
jit->seen |= SEEN_MEM;
break;
}
/*
* BPF_LDX
*/

5
arch/x86/net/bpf_jit_comp.c
View File

@ -2355,3 +2355,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
tmp : orig_prog);
return prog;
}
bool bpf_jit_supports_kfunc_call(void)
{
return true;
}

198
arch/x86/net/bpf_jit_comp32.c
View File

@ -1390,6 +1390,19 @@ static inline void emit_push_r64(const u8 src[], u8 **pprog)
*pprog = prog;
}
static void emit_push_r32(const u8 src[], u8 **pprog)
{
u8 *prog = *pprog;
int cnt = 0;
/* mov ecx,dword ptr [ebp+off] */
EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_lo));
/* push ecx */
EMIT1(0x51);
*pprog = prog;
}
static u8 get_cond_jmp_opcode(const u8 op, bool is_cmp_lo)
{
u8 jmp_cond;
@ -1459,6 +1472,174 @@ static u8 get_cond_jmp_opcode(const u8 op, bool is_cmp_lo)
return jmp_cond;
}
/* i386 kernel compiles with "-mregparm=3". From gcc document:
*
* ==== snippet ====
* regparm (number)
* On x86-32 targets, the regparm attribute causes the compiler
* to pass arguments number one to (number) if they are of integral
* type in registers EAX, EDX, and ECX instead of on the stack.
* Functions that take a variable number of arguments continue
* to be passed all of their arguments on the stack.
* ==== snippet ====
*
* The first three args of a function will be considered for
* putting into the 32bit register EAX, EDX, and ECX.
*
* Two 32bit registers are used to pass a 64bit arg.
*
* For example,
* void foo(u32 a, u32 b, u32 c, u32 d):
* u32 a: EAX
* u32 b: EDX
* u32 c: ECX
* u32 d: stack
*
* void foo(u64 a, u32 b, u32 c):
* u64 a: EAX (lo32) EDX (hi32)
* u32 b: ECX
* u32 c: stack
*
* void foo(u32 a, u64 b, u32 c):
* u32 a: EAX
* u64 b: EDX (lo32) ECX (hi32)
* u32 c: stack
*
* void foo(u32 a, u32 b, u64 c):
* u32 a: EAX
* u32 b: EDX
* u64 c: stack
*
* The return value will be stored in the EAX (and EDX for 64bit value).
*
* For example,
* u32 foo(u32 a, u32 b, u32 c):
* return value: EAX
*
* u64 foo(u32 a, u32 b, u32 c):
* return value: EAX (lo32) EDX (hi32)
*
* Notes:
* The verifier only accepts function having integer and pointers
* as its args and return value, so it does not have
* struct-by-value.
*
* emit_kfunc_call() finds out the btf_func_model by calling
* bpf_jit_find_kfunc_model(). A btf_func_model
* has the details about the number of args, size of each arg,
* and the size of the return value.
*
* It first decides how many args can be passed by EAX, EDX, and ECX.
* That will decide what args should be pushed to the stack:
* [first_stack_regno, last_stack_regno] are the bpf regnos
* that should be pushed to the stack.
*
* It will first push all args to the stack because the push
* will need to use ECX. Then, it moves
* [BPF_REG_1, first_stack_regno) to EAX, EDX, and ECX.
*
* When emitting a call (0xE8), it needs to figure out
* the jmp_offset relative to the jit-insn address immediately
* following the call (0xE8) instruction. At this point, it knows
* the end of the jit-insn address after completely translated the
* current (BPF_JMP | BPF_CALL) bpf-insn. It is passed as "end_addr"
* to the emit_kfunc_call(). Thus, it can learn the "immediate-follow-call"
* address by figuring out how many jit-insn is generated between
* the call (0xE8) and the end_addr:
* - 0-1 jit-insn (3 bytes each) to restore the esp pointer if there
* is arg pushed to the stack.
* - 0-2 jit-insns (3 bytes each) to handle the return value.
*/
static int emit_kfunc_call(const struct bpf_prog *bpf_prog, u8 *end_addr,
const struct bpf_insn *insn, u8 **pprog)
{
const u8 arg_regs[] = { IA32_EAX, IA32_EDX, IA32_ECX };
int i, cnt = 0, first_stack_regno, last_stack_regno;
int free_arg_regs = ARRAY_SIZE(arg_regs);
const struct btf_func_model *fm;
int bytes_in_stack = 0;
const u8 *cur_arg_reg;
u8 *prog = *pprog;
s64 jmp_offset;
fm = bpf_jit_find_kfunc_model(bpf_prog, insn);
if (!fm)
return -EINVAL;
first_stack_regno = BPF_REG_1;
for (i = 0; i < fm->nr_args; i++) {
int regs_needed = fm->arg_size[i] > sizeof(u32) ? 2 : 1;
if (regs_needed > free_arg_regs)
break;
free_arg_regs -= regs_needed;
first_stack_regno++;
}
/* Push the args to the stack */
last_stack_regno = BPF_REG_0 + fm->nr_args;
for (i = last_stack_regno; i >= first_stack_regno; i--) {
if (fm->arg_size[i - 1] > sizeof(u32)) {
emit_push_r64(bpf2ia32[i], &prog);
bytes_in_stack += 8;
} else {
emit_push_r32(bpf2ia32[i], &prog);
bytes_in_stack += 4;
}
}
cur_arg_reg = &arg_regs[0];
for (i = BPF_REG_1; i < first_stack_regno; i++) {
/* mov e[adc]x,dword ptr [ebp+off] */
EMIT3(0x8B, add_2reg(0x40, IA32_EBP, *cur_arg_reg++),
STACK_VAR(bpf2ia32[i][0]));
if (fm->arg_size[i - 1] > sizeof(u32))
/* mov e[adc]x,dword ptr [ebp+off] */
EMIT3(0x8B, add_2reg(0x40, IA32_EBP, *cur_arg_reg++),
STACK_VAR(bpf2ia32[i][1]));
}
if (bytes_in_stack)
/* add esp,"bytes_in_stack" */
end_addr -= 3;
/* mov dword ptr [ebp+off],edx */
if (fm->ret_size > sizeof(u32))
end_addr -= 3;
/* mov dword ptr [ebp+off],eax */
if (fm->ret_size)
end_addr -= 3;
jmp_offset = (u8 *)__bpf_call_base + insn->imm - end_addr;
if (!is_simm32(jmp_offset)) {
pr_err("unsupported BPF kernel function jmp_offset:%lld\n",
jmp_offset);
return -EINVAL;
}
EMIT1_off32(0xE8, jmp_offset);
if (fm->ret_size)
/* mov dword ptr [ebp+off],eax */
EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
STACK_VAR(bpf2ia32[BPF_REG_0][0]));
if (fm->ret_size > sizeof(u32))
/* mov dword ptr [ebp+off],edx */
EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
STACK_VAR(bpf2ia32[BPF_REG_0][1]));
if (bytes_in_stack)
/* add esp,"bytes_in_stack" */
EMIT3(0x83, add_1reg(0xC0, IA32_ESP), bytes_in_stack);
*pprog = prog;
return 0;
}
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int oldproglen, struct jit_context *ctx)
{
@ -1888,6 +2069,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
if (insn->src_reg == BPF_PSEUDO_CALL)
goto notyet;
if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
int err;
err = emit_kfunc_call(bpf_prog,
image + addrs[i],
insn, &prog);
if (err)
return err;
break;
}
func = (u8 *) __bpf_call_base + imm32;
jmp_offset = func - (image + addrs[i]);
@ -2402,3 +2595,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
tmp : orig_prog);
return prog;
}
bool bpf_jit_supports_kfunc_call(void)
{
return true;
}

1
drivers/atm/fore200e.c
View File

@ -21,7 +21,6 @@
#include <linux/module.h>
#include <linux/atmdev.h>
#include <linux/sonet.h>
#include <linux/atm_suni.h>
#include <linux/dma-mapping.h>
#include <linux/delay.h>
#include <linux/firmware.h>

6
drivers/atm/idt77252.c
View File

@ -1783,12 +1783,6 @@ set_tct(struct idt77252_dev *card, struct vc_map *vc)
/* */
/*****************************************************************************/
static __inline__ int
idt77252_fbq_level(struct idt77252_dev *card, int queue)
{
return (readl(SAR_REG_STAT) >> (16 + (queue << 2))) & 0x0f;
}
static __inline__ int
idt77252_fbq_full(struct idt77252_dev *card, int queue)
{

2
drivers/atm/iphase.c
View File

@ -680,7 +680,7 @@ static void ia_tx_poll (IADEV *iadev) {
skb1 = skb_dequeue(&iavcc->txing_skb);
}
if (!skb1) {
IF_EVENT(printk("IA: Vci %d - skb not found requed\n",vcc->vci);)
IF_EVENT(printk("IA: Vci %d - skb not found requeued\n",vcc->vci);)
ia_enque_head_rtn_q (&iadev->tx_return_q, rtne);
break;
}

1
drivers/atm/suni.c
View File

@ -21,7 +21,6 @@
#include <linux/timer.h>
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/atm_suni.h>
#include <linux/slab.h>
#include <asm/param.h>
#include <linux/uaccess.h>

7
drivers/bcma/driver_mips.c
View File

@ -52,13 +52,6 @@ static inline u32 mips_read32(struct bcma_drv_mips *mcore,
return bcma_read32(mcore->core, offset);
}
static inline void mips_write32(struct bcma_drv_mips *mcore,
u16 offset,
u32 value)
{
bcma_write32(mcore->core, offset, value);
}
static u32 bcma_core_mips_irqflag(struct bcma_device *dev)
{
u32 flag;

10
drivers/bluetooth/Kconfig
View File

@ -425,4 +425,14 @@ config BT_HCIRSI
Say Y here to compile support for HCI over Redpine into the
kernel or say M to compile as a module.
config BT_VIRTIO
tristate "Virtio Bluetooth driver"
depends on VIRTIO
help
Virtio Bluetooth support driver.
This driver supports Virtio Bluetooth devices.
Say Y here to compile support for HCI over Virtio into the
kernel or say M to compile as a module.
endmenu

2
drivers/bluetooth/Makefile
View File

@ -26,6 +26,8 @@ obj-$(CONFIG_BT_BCM) += btbcm.o
obj-$(CONFIG_BT_RTL) += btrtl.o
obj-$(CONFIG_BT_QCA) += btqca.o
obj-$(CONFIG_BT_VIRTIO) += virtio_bt.o
obj-$(CONFIG_BT_HCIUART_NOKIA) += hci_nokia.o
obj-$(CONFIG_BT_HCIRSI) += btrsi.o

232
drivers/bluetooth/btintel.c
View File

@ -24,6 +24,14 @@
#define ECDSA_OFFSET 644
#define ECDSA_HEADER_LEN 320
#define CMD_WRITE_BOOT_PARAMS 0xfc0e
struct cmd_write_boot_params {
u32 boot_addr;
u8 fw_build_num;
u8 fw_build_ww;
u8 fw_build_yy;
} __packed;
int btintel_check_bdaddr(struct hci_dev *hdev)
{
struct hci_rp_read_bd_addr *bda;
@ -208,10 +216,39 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code)
}
EXPORT_SYMBOL_GPL(btintel_hw_error);
void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver)
int btintel_version_info(struct hci_dev *hdev, struct intel_version *ver)
{
const char *variant;
/* The hardware platform number has a fixed value of 0x37 and
* for now only accept this single value.
*/
if (ver->hw_platform != 0x37) {
bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)",
ver->hw_platform);
return -EINVAL;
}
/* Check for supported iBT hardware variants of this firmware
* loading method.
*
* This check has been put in place to ensure correct forward
* compatibility options when newer hardware variants come along.
*/
switch (ver->hw_variant) {
case 0x0b: /* SfP */
case 0x0c: /* WsP */
case 0x11: /* JfP */
case 0x12: /* ThP */
case 0x13: /* HrP */
case 0x14: /* CcP */
break;
default:
bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
ver->hw_variant);
return -EINVAL;
}
switch (ver->fw_variant) {
case 0x06:
variant = "Bootloader";
@ -220,13 +257,16 @@ void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver)
variant = "Firmware";
break;
default:
return;
bt_dev_err(hdev, "Unsupported firmware variant(%02x)", ver->fw_variant);
return -EINVAL;
}
bt_dev_info(hdev, "%s revision %u.%u build %u week %u %u",
variant, ver->fw_revision >> 4, ver->fw_revision & 0x0f,
ver->fw_build_num, ver->fw_build_ww,
2000 + ver->fw_build_yy);
return 0;
}
EXPORT_SYMBOL_GPL(btintel_version_info);
@ -364,13 +404,56 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver)
}
EXPORT_SYMBOL_GPL(btintel_read_version);
void btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *version)
int btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *version)
{
const char *variant;
/* The hardware platform number has a fixed value of 0x37 and
* for now only accept this single value.
*/
if (INTEL_HW_PLATFORM(version->cnvi_bt) != 0x37) {
bt_dev_err(hdev, "Unsupported Intel hardware platform (0x%2x)",
INTEL_HW_PLATFORM(version->cnvi_bt));
return -EINVAL;
}
/* Check for supported iBT hardware variants of this firmware
* loading method.
*
* This check has been put in place to ensure correct forward
* compatibility options when newer hardware variants come along.
*/
switch (INTEL_HW_VARIANT(version->cnvi_bt)) {
case 0x17: /* TyP */
case 0x18: /* Slr */
case 0x19: /* Slr-F */
break;
default:
bt_dev_err(hdev, "Unsupported Intel hardware variant (0x%x)",
INTEL_HW_VARIANT(version->cnvi_bt));
return -EINVAL;
}
switch (version->img_type) {
case 0x01:
variant = "Bootloader";
/* It is required that every single firmware fragment is acknowledged
* with a command complete event. If the boot parameters indicate
* that this bootloader does not send them, then abort the setup.
*/
if (version->limited_cce != 0x00) {
bt_dev_err(hdev, "Unsupported Intel firmware loading method (0x%x)",
version->limited_cce);
return -EINVAL;
}
/* Secure boot engine type should be either 1 (ECDSA) or 0 (RSA) */
if (version->sbe_type > 0x01) {
bt_dev_err(hdev, "Unsupported Intel secure boot engine type (0x%x)",
version->sbe_type);
return -EINVAL;
}
bt_dev_info(hdev, "Device revision is %u", version->dev_rev_id);
bt_dev_info(hdev, "Secure boot is %s",
version->secure_boot ? "enabled" : "disabled");
@ -389,15 +472,14 @@ void btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *ve
break;
default:
bt_dev_err(hdev, "Unsupported image type(%02x)", version->img_type);
goto done;
return -EINVAL;
}
bt_dev_info(hdev, "%s timestamp %u.%u buildtype %u build %u", variant,
2000 + (version->timestamp >> 8), version->timestamp & 0xff,
version->build_type, version->build_num);
done:
return;
return 0;
}
EXPORT_SYMBOL_GPL(btintel_version_info_tlv);
@ -455,12 +537,23 @@ int btintel_read_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *ver
version->img_type = tlv->val[0];
break;
case INTEL_TLV_TIME_STAMP:
/* If image type is Operational firmware (0x03), then
* running FW Calendar Week and Year information can
* be extracted from Timestamp information
*/
version->min_fw_build_cw = tlv->val[0];
version->min_fw_build_yy = tlv->val[1];
version->timestamp = get_unaligned_le16(tlv->val);
break;
case INTEL_TLV_BUILD_TYPE:
version->build_type = tlv->val[0];
break;
case INTEL_TLV_BUILD_NUM:
/* If image type is Operational firmware (0x03), then
* running FW build number can be extracted from the
* Build information
*/
version->min_fw_build_nn = tlv->val[0];
version->build_num = get_unaligned_le32(tlv->val);
break;
case INTEL_TLV_SECURE_BOOT:
@ -841,7 +934,7 @@ static int btintel_sfi_ecdsa_header_secure_send(struct hci_dev *hdev,
static int btintel_download_firmware_payload(struct hci_dev *hdev,
const struct firmware *fw,
u32 *boot_param, size_t offset)
size_t offset)
{
int err;
const u8 *fw_ptr;
@ -854,20 +947,6 @@ static int btintel_download_firmware_payload(struct hci_dev *hdev,
while (fw_ptr - fw->data < fw->size) {
struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
/* Each SKU has a different reset parameter to use in the
* HCI_Intel_Reset command and it is embedded in the firmware
* data. So, instead of using static value per SKU, check
* the firmware data and save it for later use.
*/
if (le16_to_cpu(cmd->opcode) == 0xfc0e) {
/* The boot parameter is the first 32-bit value
* and rest of 3 octets are reserved.
*/
*boot_param = get_unaligned_le32(fw_ptr + sizeof(*cmd));
bt_dev_dbg(hdev, "boot_param=0x%x", *boot_param);
}
frag_len += sizeof(*cmd) + cmd->plen;
/* The parameter length of the secure send command requires
@ -896,28 +975,131 @@ static int btintel_download_firmware_payload(struct hci_dev *hdev,
return err;
}
static bool btintel_firmware_version(struct hci_dev *hdev,
u8 num, u8 ww, u8 yy,
const struct firmware *fw,
u32 *boot_addr)
{
const u8 *fw_ptr;
fw_ptr = fw->data;
while (fw_ptr - fw->data < fw->size) {
struct hci_command_hdr *cmd = (void *)(fw_ptr);
/* Each SKU has a different reset parameter to use in the
* HCI_Intel_Reset command and it is embedded in the firmware
* data. So, instead of using static value per SKU, check
* the firmware data and save it for later use.
*/
if (le16_to_cpu(cmd->opcode) == CMD_WRITE_BOOT_PARAMS) {
struct cmd_write_boot_params *params;
params = (void *)(fw_ptr + sizeof(*cmd));
bt_dev_info(hdev, "Boot Address: 0x%x",
le32_to_cpu(params->boot_addr));
bt_dev_info(hdev, "Firmware Version: %u-%u.%u",
params->fw_build_num, params->fw_build_ww,
params->fw_build_yy);
return (num == params->fw_build_num &&
ww == params->fw_build_ww &&
yy == params->fw_build_yy);
}
fw_ptr += sizeof(*cmd) + cmd->plen;
}
return false;
}
int btintel_download_firmware(struct hci_dev *hdev,
struct intel_version *ver,
const struct firmware *fw,
u32 *boot_param)
{
int err;
/* SfP and WsP don't seem to update the firmware version on file
* so version checking is currently not possible.
*/
switch (ver->hw_variant) {
case 0x0b: /* SfP */
case 0x0c: /* WsP */
/* Skip version checking */
break;
default:
/* Skip reading firmware file version in bootloader mode */
if (ver->fw_variant == 0x06)
break;
/* Skip download if firmware has the same version */
if (btintel_firmware_version(hdev, ver->fw_build_num,
ver->fw_build_ww, ver->fw_build_yy,
fw, boot_param)) {
bt_dev_info(hdev, "Firmware already loaded");
/* Return -EALREADY to indicate that the firmware has
* already been loaded.
*/
return -EALREADY;
}
}
/* The firmware variant determines if the device is in bootloader
* mode or is running operational firmware. The value 0x06 identifies
* the bootloader and the value 0x23 identifies the operational
* firmware.
*
* If the firmware version has changed that means it needs to be reset
* to bootloader when operational so the new firmware can be loaded.
*/
if (ver->fw_variant == 0x23)
return -EINVAL;
err = btintel_sfi_rsa_header_secure_send(hdev, fw);
if (err)
return err;
return btintel_download_firmware_payload(hdev, fw, boot_param,
RSA_HEADER_LEN);
return btintel_download_firmware_payload(hdev, fw, RSA_HEADER_LEN);
}
EXPORT_SYMBOL_GPL(btintel_download_firmware);
int btintel_download_firmware_newgen(struct hci_dev *hdev,
struct intel_version_tlv *ver,
const struct firmware *fw, u32 *boot_param,
u8 hw_variant, u8 sbe_type)
{
int err;
u32 css_header_ver;
/* Skip reading firmware file version in bootloader mode */
if (ver->img_type != 0x01) {
/* Skip download if firmware has the same version */
if (btintel_firmware_version(hdev, ver->min_fw_build_nn,
ver->min_fw_build_cw,
ver->min_fw_build_yy,
fw, boot_param)) {
bt_dev_info(hdev, "Firmware already loaded");
/* Return -EALREADY to indicate that firmware has
* already been loaded.
*/
return -EALREADY;
}
}
/* The firmware variant determines if the device is in bootloader
* mode or is running operational firmware. The value 0x01 identifies
* the bootloader and the value 0x03 identifies the operational
* firmware.
*
* If the firmware version has changed that means it needs to be reset
* to bootloader when operational so the new firmware can be loaded.
*/
if (ver->img_type == 0x03)
return -EINVAL;
/* iBT hardware variants 0x0b, 0x0c, 0x11, 0x12, 0x13, 0x14 support
* only RSA secure boot engine. Hence, the corresponding sfi file will
* have RSA header of 644 bytes followed by Command Buffer.
@ -947,7 +1129,7 @@ int btintel_download_firmware_newgen(struct hci_dev *hdev,
if (err)
return err;
err = btintel_download_firmware_payload(hdev, fw, boot_param, RSA_HEADER_LEN);
err = btintel_download_firmware_payload(hdev, fw, RSA_HEADER_LEN);
if (err)
return err;
} else if (hw_variant >= 0x17) {
@ -968,7 +1150,6 @@ int btintel_download_firmware_newgen(struct hci_dev *hdev,
return err;
err = btintel_download_firmware_payload(hdev, fw,
boot_param,
RSA_HEADER_LEN + ECDSA_HEADER_LEN);
if (err)
return err;
@ -978,7 +1159,6 @@ int btintel_download_firmware_newgen(struct hci_dev *hdev,
return err;
err = btintel_download_firmware_payload(hdev, fw,
boot_param,
RSA_HEADER_LEN + ECDSA_HEADER_LEN);
if (err)
return err;

19
drivers/bluetooth/btintel.h
View File

@ -148,8 +148,8 @@ int btintel_set_diag(struct hci_dev *hdev, bool enable);
int btintel_set_diag_mfg(struct hci_dev *hdev, bool enable);
void btintel_hw_error(struct hci_dev *hdev, u8 code);
void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver);
void btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *version);
int btintel_version_info(struct hci_dev *hdev, struct intel_version *ver);
int btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *version);
int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen,
const void *param);
int btintel_load_ddc_config(struct hci_dev *hdev, const char *ddc_name);
@ -163,9 +163,10 @@ struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read,
int btintel_send_intel_reset(struct hci_dev *hdev, u32 boot_param);
int btintel_read_boot_params(struct hci_dev *hdev,
struct intel_boot_params *params);
int btintel_download_firmware(struct hci_dev *dev, const struct firmware *fw,
u32 *boot_param);
int btintel_download_firmware(struct hci_dev *dev, struct intel_version *ver,
const struct firmware *fw, u32 *boot_param);
int btintel_download_firmware_newgen(struct hci_dev *hdev,
struct intel_version_tlv *ver,
const struct firmware *fw,
u32 *boot_param, u8 hw_variant,
u8 sbe_type);
@ -210,14 +211,16 @@ static inline void btintel_hw_error(struct hci_dev *hdev, u8 code)
{
}
static inline void btintel_version_info(struct hci_dev *hdev,
struct intel_version *ver)
static inline int btintel_version_info(struct hci_dev *hdev,
struct intel_version *ver)
{
return -EOPNOTSUPP;
}
static inline void btintel_version_info_tlv(struct hci_dev *hdev,
struct intel_version_tlv *version)
static inline int btintel_version_info_tlv(struct hci_dev *hdev,
struct intel_version_tlv *version)
{
return -EOPNOTSUPP;
}
static inline int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type,

424
drivers/bluetooth/btusb.c
View File

@ -399,7 +399,9 @@ static const struct usb_device_id blacklist_table[] = {
/* MediaTek Bluetooth devices */
{ USB_VENDOR_AND_INTERFACE_INFO(0x0e8d, 0xe0, 0x01, 0x01),
.driver_info = BTUSB_MEDIATEK },
.driver_info = BTUSB_MEDIATEK |
BTUSB_WIDEBAND_SPEECH |
BTUSB_VALID_LE_STATES },
/* Additional MediaTek MT7615E Bluetooth devices */
{ USB_DEVICE(0x13d3, 0x3560), .driver_info = BTUSB_MEDIATEK},
@ -455,6 +457,8 @@ static const struct usb_device_id blacklist_table[] = {
BTUSB_WIDEBAND_SPEECH },
{ USB_DEVICE(0x0bda, 0xc123), .driver_info = BTUSB_REALTEK |
BTUSB_WIDEBAND_SPEECH },
{ USB_DEVICE(0x0cb5, 0xc547), .driver_info = BTUSB_REALTEK |
BTUSB_WIDEBAND_SPEECH },
/* Silicon Wave based devices */
{ USB_DEVICE(0x0c10, 0x0000), .driver_info = BTUSB_SWAVE },
@ -2400,7 +2404,7 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
return -EILSEQ;
}
static bool btusb_setup_intel_new_get_fw_name(struct intel_version *ver,
static int btusb_setup_intel_new_get_fw_name(struct intel_version *ver,
struct intel_boot_params *params,
char *fw_name, size_t len,
const char *suffix)
@ -2424,9 +2428,10 @@ static bool btusb_setup_intel_new_get_fw_name(struct intel_version *ver,
suffix);
break;
default:
return false;
return -EINVAL;
}
return true;
return 0;
}
static void btusb_setup_intel_newgen_get_fw_name(const struct intel_version_tlv *ver_tlv,
@ -2444,6 +2449,44 @@ static void btusb_setup_intel_newgen_get_fw_name(const struct intel_version_tlv
suffix);
}
static int btusb_download_wait(struct hci_dev *hdev, ktime_t calltime, int msec)
{
struct btusb_data *data = hci_get_drvdata(hdev);
ktime_t delta, rettime;
unsigned long long duration;
int err;
set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
bt_dev_info(hdev, "Waiting for firmware download to complete");
err = wait_on_bit_timeout(&data->flags, BTUSB_DOWNLOADING,
TASK_INTERRUPTIBLE,
msecs_to_jiffies(msec));
if (err == -EINTR) {
bt_dev_err(hdev, "Firmware loading interrupted");
return err;
}
if (err) {
bt_dev_err(hdev, "Firmware loading timeout");
return -ETIMEDOUT;
}
if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) {
bt_dev_err(hdev, "Firmware loading failed");
return -ENOEXEC;
}
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long)ktime_to_ns(delta) >> 10;
bt_dev_info(hdev, "Firmware loaded in %llu usecs", duration);
return 0;
}
static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
struct intel_version_tlv *ver,
u32 *boot_param)
@ -2452,19 +2495,11 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
char fwname[64];
int err;
struct btusb_data *data = hci_get_drvdata(hdev);
ktime_t calltime;
if (!ver || !boot_param)
return -EINVAL;
/* The hardware platform number has a fixed value of 0x37 and
* for now only accept this single value.
*/
if (INTEL_HW_PLATFORM(ver->cnvi_bt) != 0x37) {
bt_dev_err(hdev, "Unsupported Intel hardware platform (0x%2x)",
INTEL_HW_PLATFORM(ver->cnvi_bt));
return -EINVAL;
}
/* The firmware variant determines if the device is in bootloader
* mode or is running operational firmware. The value 0x03 identifies
* the bootloader and the value 0x23 identifies the operational
@ -2481,50 +2516,6 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
if (ver->img_type == 0x03) {
clear_bit(BTUSB_BOOTLOADER, &data->flags);
btintel_check_bdaddr(hdev);
return 0;
}
/* Check for supported iBT hardware variants of this firmware
* loading method.
*
* This check has been put in place to ensure correct forward
* compatibility options when newer hardware variants come along.
*/
switch (INTEL_HW_VARIANT(ver->cnvi_bt)) {
case 0x17: /* TyP */
case 0x18: /* Slr */
case 0x19: /* Slr-F */
break;
default:
bt_dev_err(hdev, "Unsupported Intel hardware variant (0x%x)",
INTEL_HW_VARIANT(ver->cnvi_bt));
return -EINVAL;
}
/* If the device is not in bootloader mode, then the only possible
* choice is to return an error and abort the device initialization.
*/
if (ver->img_type != 0x01) {
bt_dev_err(hdev, "Unsupported Intel firmware variant (0x%x)",
ver->img_type);
return -ENODEV;
}
/* It is required that every single firmware fragment is acknowledged
* with a command complete event. If the boot parameters indicate
* that this bootloader does not send them, then abort the setup.
*/
if (ver->limited_cce != 0x00) {
bt_dev_err(hdev, "Unsupported Intel firmware loading method (0x%x)",
ver->limited_cce);
return -EINVAL;
}
/* Secure boot engine type should be either 1 (ECDSA) or 0 (RSA) */
if (ver->sbe_type > 0x01) {
bt_dev_err(hdev, "Unsupported Intel secure boot engine type (0x%x)",
ver->sbe_type);
return -EINVAL;
}
/* If the OTP has no valid Bluetooth device address, then there will
@ -2538,7 +2529,8 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
btusb_setup_intel_newgen_get_fw_name(ver, fwname, sizeof(fwname), "sfi");
err = request_firmware(&fw, fwname, &hdev->dev);
if (err < 0) {
bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", err);
bt_dev_err(hdev, "Failed to load Intel firmware file %s (%d)",
fwname, err);
return err;
}
@ -2551,22 +2543,28 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
goto done;
}
calltime = ktime_get();
set_bit(BTUSB_DOWNLOADING, &data->flags);
/* Start firmware downloading and get boot parameter */
err = btintel_download_firmware_newgen(hdev, fw, boot_param,
err = btintel_download_firmware_newgen(hdev, ver, fw, boot_param,
INTEL_HW_VARIANT(ver->cnvi_bt),
ver->sbe_type);
if (err < 0) {
if (err == -EALREADY) {
/* Firmware has already been loaded */
set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
err = 0;
goto done;
}
/* When FW download fails, send Intel Reset to retry
* FW download.
*/
btintel_reset_to_bootloader(hdev);
goto done;
}
set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
bt_dev_info(hdev, "Waiting for firmware download to complete");
/* Before switching the device into operational mode and with that
* booting the loaded firmware, wait for the bootloader notification
@ -2579,26 +2577,9 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
* and thus just timeout if that happens and fail the setup
* of this device.
*/
err = wait_on_bit_timeout(&data->flags, BTUSB_DOWNLOADING,
TASK_INTERRUPTIBLE,
msecs_to_jiffies(5000));
if (err == -EINTR) {
bt_dev_err(hdev, "Firmware loading interrupted");
goto done;
}
if (err) {
bt_dev_err(hdev, "Firmware loading timeout");
err = -ETIMEDOUT;
err = btusb_download_wait(hdev, calltime, 5000);
if (err == -ETIMEDOUT)
btintel_reset_to_bootloader(hdev);
goto done;
}
if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) {
bt_dev_err(hdev, "Firmware loading failed");
err = -ENOEXEC;
goto done;
}
done:
release_firmware(fw);
@ -2614,41 +2595,11 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
char fwname[64];
int err;
struct btusb_data *data = hci_get_drvdata(hdev);
ktime_t calltime;
if (!ver || !params)
return -EINVAL;
/* The hardware platform number has a fixed value of 0x37 and
* for now only accept this single value.
*/
if (ver->hw_platform != 0x37) {
bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)",
ver->hw_platform);
return -EINVAL;
}
/* Check for supported iBT hardware variants of this firmware
* loading method.
*
* This check has been put in place to ensure correct forward
* compatibility options when newer hardware variants come along.
*/
switch (ver->hw_variant) {
case 0x0b: /* SfP */
case 0x0c: /* WsP */
case 0x11: /* JfP */
case 0x12: /* ThP */
case 0x13: /* HrP */
case 0x14: /* CcP */
break;
default:
bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
ver->hw_variant);
return -EINVAL;
}
btintel_version_info(hdev, ver);
/* The firmware variant determines if the device is in bootloader
* mode or is running operational firmware. The value 0x06 identifies
* the bootloader and the value 0x23 identifies the operational
@ -2665,16 +2616,18 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
if (ver->fw_variant == 0x23) {
clear_bit(BTUSB_BOOTLOADER, &data->flags);
btintel_check_bdaddr(hdev);
return 0;
}
/* If the device is not in bootloader mode, then the only possible
* choice is to return an error and abort the device initialization.
*/
if (ver->fw_variant != 0x06) {
bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)",
ver->fw_variant);
return -ENODEV;
/* SfP and WsP don't seem to update the firmware version on file
* so version checking is currently possible.
*/
switch (ver->hw_variant) {
case 0x0b: /* SfP */
case 0x0c: /* WsP */
return 0;
}
/* Proceed to download to check if the version matches */
goto download;
}
/* Read the secure boot parameters to identify the operating
@ -2702,6 +2655,7 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
}
download:
/* With this Intel bootloader only the hardware variant and device
* revision information are used to select the right firmware for SfP
* and WsP.
@ -2725,14 +2679,15 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
*/
err = btusb_setup_intel_new_get_fw_name(ver, params, fwname,
sizeof(fwname), "sfi");
if (!err) {
if (err < 0) {
bt_dev_err(hdev, "Unsupported Intel firmware naming");
return -EINVAL;
}
err = request_firmware(&fw, fwname, &hdev->dev);
if (err < 0) {
bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", err);
bt_dev_err(hdev, "Failed to load Intel firmware file %s (%d)",
fwname, err);
return err;
}
@ -2745,20 +2700,26 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
goto done;
}
calltime = ktime_get();
set_bit(BTUSB_DOWNLOADING, &data->flags);
/* Start firmware downloading and get boot parameter */
err = btintel_download_firmware(hdev, fw, boot_param);
err = btintel_download_firmware(hdev, ver, fw, boot_param);
if (err < 0) {
if (err == -EALREADY) {
/* Firmware has already been loaded */
set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
err = 0;
goto done;
}
/* When FW download fails, send Intel Reset to retry
* FW download.
*/
btintel_reset_to_bootloader(hdev);
goto done;
}
set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
bt_dev_info(hdev, "Waiting for firmware download to complete");
/* Before switching the device into operational mode and with that
* booting the loaded firmware, wait for the bootloader notification
@ -2771,84 +2732,57 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
* and thus just timeout if that happens and fail the setup
* of this device.
*/
err = wait_on_bit_timeout(&data->flags, BTUSB_DOWNLOADING,
TASK_INTERRUPTIBLE,
msecs_to_jiffies(5000));
if (err == -EINTR) {
bt_dev_err(hdev, "Firmware loading interrupted");
goto done;
}
if (err) {
bt_dev_err(hdev, "Firmware loading timeout");
err = -ETIMEDOUT;
err = btusb_download_wait(hdev, calltime, 5000);
if (err == -ETIMEDOUT)
btintel_reset_to_bootloader(hdev);
goto done;
}
if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) {
bt_dev_err(hdev, "Firmware loading failed");
err = -ENOEXEC;
goto done;
}
done:
release_firmware(fw);
return err;
}
static int btusb_setup_intel_new(struct hci_dev *hdev)
static int btusb_boot_wait(struct hci_dev *hdev, ktime_t calltime, int msec)
{
struct btusb_data *data = hci_get_drvdata(hdev);
struct intel_version ver;
struct intel_boot_params params;
u32 boot_param;
char ddcname[64];
ktime_t calltime, delta, rettime;
ktime_t delta, rettime;
unsigned long long duration;
int err;
struct intel_debug_features features;
BT_DBG("%s", hdev->name);
bt_dev_info(hdev, "Waiting for device to boot");
/* Set the default boot parameter to 0x0 and it is updated to
* SKU specific boot parameter after reading Intel_Write_Boot_Params
* command while downloading the firmware.
*/
boot_param = 0x00000000;
calltime = ktime_get();
/* Read the Intel version information to determine if the device
* is in bootloader mode or if it already has operational firmware
* loaded.
*/
err = btintel_read_version(hdev, &ver);
if (err) {
bt_dev_err(hdev, "Intel Read version failed (%d)", err);
btintel_reset_to_bootloader(hdev);
return err;
err = wait_on_bit_timeout(&data->flags, BTUSB_BOOTING,
TASK_INTERRUPTIBLE,
msecs_to_jiffies(msec));
if (err == -EINTR) {
bt_dev_err(hdev, "Device boot interrupted");
return -EINTR;
}
err = btusb_intel_download_firmware(hdev, &ver, &params, &boot_param);
if (err)
return err;
/* controller is already having an operational firmware */
if (ver.fw_variant == 0x23)
goto finish;
if (err) {
bt_dev_err(hdev, "Device boot timeout");
return -ETIMEDOUT;
}
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
bt_dev_info(hdev, "Firmware loaded in %llu usecs", duration);
bt_dev_info(hdev, "Device booted in %llu usecs", duration);
return 0;
}
static int btusb_intel_boot(struct hci_dev *hdev, u32 boot_addr)
{
struct btusb_data *data = hci_get_drvdata(hdev);
ktime_t calltime;
int err;
calltime = ktime_get();
set_bit(BTUSB_BOOTING, &data->flags);
err = btintel_send_intel_reset(hdev, boot_param);
err = btintel_send_intel_reset(hdev, boot_addr);
if (err) {
bt_dev_err(hdev, "Intel Soft Reset failed (%d)", err);
btintel_reset_to_bootloader(hdev);
@ -2862,35 +2796,64 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
* 1 second. However if that happens, then just fail the setup
* since something went wrong.
*/
bt_dev_info(hdev, "Waiting for device to boot");
err = wait_on_bit_timeout(&data->flags, BTUSB_BOOTING,
TASK_INTERRUPTIBLE,
msecs_to_jiffies(1000));
if (err == -EINTR) {
bt_dev_err(hdev, "Device boot interrupted");
return -EINTR;
}
if (err) {
bt_dev_err(hdev, "Device boot timeout");
err = btusb_boot_wait(hdev, calltime, 1000);
if (err == -ETIMEDOUT)
btintel_reset_to_bootloader(hdev);
return -ETIMEDOUT;
return err;
}
static int btusb_setup_intel_new(struct hci_dev *hdev)
{
struct btusb_data *data = hci_get_drvdata(hdev);
struct intel_version ver;
struct intel_boot_params params;
u32 boot_param;
char ddcname[64];
int err;
struct intel_debug_features features;
BT_DBG("%s", hdev->name);
/* Set the default boot parameter to 0x0 and it is updated to
* SKU specific boot parameter after reading Intel_Write_Boot_Params
* command while downloading the firmware.
*/
boot_param = 0x00000000;
/* Read the Intel version information to determine if the device
* is in bootloader mode or if it already has operational firmware
* loaded.
*/
err = btintel_read_version(hdev, &ver);
if (err) {
bt_dev_err(hdev, "Intel Read version failed (%d)", err);
btintel_reset_to_bootloader(hdev);
return err;
}
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
err = btintel_version_info(hdev, &ver);
if (err)
return err;
bt_dev_info(hdev, "Device booted in %llu usecs", duration);
err = btusb_intel_download_firmware(hdev, &ver, &params, &boot_param);
if (err)
return err;
/* controller is already having an operational firmware */
if (ver.fw_variant == 0x23)
goto finish;
err = btusb_intel_boot(hdev, boot_param);
if (err)
return err;
clear_bit(BTUSB_BOOTLOADER, &data->flags);
err = btusb_setup_intel_new_get_fw_name(&ver, &params, ddcname,
sizeof(ddcname), "ddc");
if (!err) {
if (err < 0) {
bt_dev_err(hdev, "Unsupported Intel firmware naming");
} else {
/* Once the device is running in operational mode, it needs to
@ -2947,8 +2910,6 @@ static int btusb_setup_intel_newgen(struct hci_dev *hdev)
struct btusb_data *data = hci_get_drvdata(hdev);
u32 boot_param;
char ddcname[64];
ktime_t calltime, delta, rettime;
unsigned long long duration;
int err;
struct intel_debug_features features;
struct intel_version_tlv version;
@ -2961,8 +2922,6 @@ static int btusb_setup_intel_newgen(struct hci_dev *hdev)
*/
boot_param = 0x00000000;
calltime = ktime_get();
/* Read the Intel version information to determine if the device
* is in bootloader mode or if it already has operational firmware
* loaded.
@ -2974,7 +2933,9 @@ static int btusb_setup_intel_newgen(struct hci_dev *hdev)
return err;
}
btintel_version_info_tlv(hdev, &version);
err = btintel_version_info_tlv(hdev, &version);
if (err)
return err;
err = btusb_intel_download_firmware_newgen(hdev, &version, &boot_param);
if (err)
@ -2984,52 +2945,9 @@ static int btusb_setup_intel_newgen(struct hci_dev *hdev)
if (version.img_type == 0x03)
goto finish;
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long)ktime_to_ns(delta) >> 10;
bt_dev_info(hdev, "Firmware loaded in %llu usecs", duration);
calltime = ktime_get();
set_bit(BTUSB_BOOTING, &data->flags);
err = btintel_send_intel_reset(hdev, boot_param);
if (err) {
bt_dev_err(hdev, "Intel Soft Reset failed (%d)", err);
btintel_reset_to_bootloader(hdev);
err = btusb_intel_boot(hdev, boot_param);
if (err)
return err;
}
/* The bootloader will not indicate when the device is ready. This
* is done by the operational firmware sending bootup notification.
*
* Booting into operational firmware should not take longer than
* 1 second. However if that happens, then just fail the setup
* since something went wrong.
*/
bt_dev_info(hdev, "Waiting for device to boot");
err = wait_on_bit_timeout(&data->flags, BTUSB_BOOTING,
TASK_INTERRUPTIBLE,
msecs_to_jiffies(1000));
if (err == -EINTR) {
bt_dev_err(hdev, "Device boot interrupted");
return -EINTR;
}
if (err) {
bt_dev_err(hdev, "Device boot timeout");
btintel_reset_to_bootloader(hdev);
return -ETIMEDOUT;
}
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long)ktime_to_ns(delta) >> 10;
bt_dev_info(hdev, "Device booted in %llu usecs", duration);
clear_bit(BTUSB_BOOTLOADER, &data->flags);
@ -3495,7 +3413,7 @@ static int btusb_mtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwnam
fw_ptr = fw->data;
fw_bin_ptr = fw_ptr;
globaldesc = (struct btmtk_global_desc *)(fw_ptr + MTK_FW_ROM_PATCH_HEADER_SIZE);
section_num = globaldesc->section_num;
section_num = le32_to_cpu(globaldesc->section_num);
for (i = 0; i < section_num; i++) {
first_block = 1;
@ -3503,8 +3421,8 @@ static int btusb_mtk_setup_firmware_79xx(struct hci_dev *hdev, const char *fwnam
sectionmap = (struct btmtk_section_map *)(fw_ptr + MTK_FW_ROM_PATCH_HEADER_SIZE +
MTK_FW_ROM_PATCH_GD_SIZE + MTK_FW_ROM_PATCH_SEC_MAP_SIZE * i);
section_offset = sectionmap->secoffset;
dl_size = sectionmap->bin_info_spec.dlsize;
section_offset = le32_to_cpu(sectionmap->secoffset);
dl_size = le32_to_cpu(sectionmap->bin_info_spec.dlsize);
if (dl_size > 0) {
retry = 20;
@ -3740,7 +3658,7 @@ static int btusb_mtk_setup(struct hci_dev *hdev)
int err, status;
u32 dev_id;
char fw_bin_name[64];
u32 fw_version;
u32 fw_version = 0;
u8 param;
calltime = ktime_get();

19
drivers/bluetooth/hci_bcm.c
View File

@ -68,6 +68,8 @@ struct bcm_device_data {
* deassert = Bluetooth device may sleep when sleep criteria are met
* @shutdown: BT_REG_ON pin,
* power up or power down Bluetooth device internal regulators
* @reset: BT_RST_N pin,
* active low resets the Bluetooth logic core
* @set_device_wakeup: callback to toggle BT_WAKE pin
* either by accessing @device_wakeup or by calling @btlp
* @set_shutdown: callback to toggle BT_REG_ON pin
@ -101,6 +103,7 @@ struct bcm_device {
const char *name;
struct gpio_desc *device_wakeup;
struct gpio_desc *shutdown;
struct gpio_desc *reset;
int (*set_device_wakeup)(struct bcm_device *, bool);
int (*set_shutdown)(struct bcm_device *, bool);
#ifdef CONFIG_ACPI
@ -985,6 +988,15 @@ static int bcm_gpio_set_device_wakeup(struct bcm_device *dev, bool awake)
static int bcm_gpio_set_shutdown(struct bcm_device *dev, bool powered)
{
gpiod_set_value_cansleep(dev->shutdown, powered);
if (dev->reset)
/*
* The reset line is asserted on powerdown and deasserted
* on poweron so the inverse of powered is used. Notice
* that the GPIO line BT_RST_N needs to be specified as
* active low in the device tree or similar system
* description.
*/
gpiod_set_value_cansleep(dev->reset, !powered);
return 0;
}
@ -1050,6 +1062,11 @@ static int bcm_get_resources(struct bcm_device *dev)
if (IS_ERR(dev->shutdown))
return PTR_ERR(dev->shutdown);
dev->reset = devm_gpiod_get_optional(dev->dev, "reset",
GPIOD_OUT_LOW);
if (IS_ERR(dev->reset))
return PTR_ERR(dev->reset);
dev->set_device_wakeup = bcm_gpio_set_device_wakeup;
dev->set_shutdown = bcm_gpio_set_shutdown;
@ -1482,6 +1499,8 @@ static struct bcm_device_data bcm43438_device_data = {
static const struct of_device_id bcm_bluetooth_of_match[] = {
{ .compatible = "brcm,bcm20702a1" },
{ .compatible = "brcm,bcm4329-bt" },
{ .compatible = "brcm,bcm4330-bt" },
{ .compatible = "brcm,bcm4334-bt" },
{ .compatible = "brcm,bcm4345c5" },
{ .compatible = "brcm,bcm4330-bt" },
{ .compatible = "brcm,bcm43438-bt", .data = &bcm43438_device_data },

7
drivers/bluetooth/hci_intel.c
View File

@ -735,7 +735,7 @@ static int intel_setup(struct hci_uart *hu)
set_bit(STATE_DOWNLOADING, &intel->flags);
/* Start firmware downloading and get boot parameter */
err = btintel_download_firmware(hdev, fw, &boot_param);
err = btintel_download_firmware(hdev, &ver, fw, &boot_param);
if (err < 0)
goto done;
@ -784,7 +784,10 @@ static int intel_setup(struct hci_uart *hu)
done:
release_firmware(fw);
if (err < 0)
/* Check if there was an error and if is not -EALREADY which means the
* firmware has already been loaded.
*/
if (err < 0 && err != -EALREADY)
return err;
/* We need to restore the default speed before Intel reset */

17
drivers/bluetooth/hci_qca.c
View File

@ -1066,7 +1066,7 @@ static void qca_controller_memdump(struct work_struct *work)
* packets in the buffer.
*/
/* For QCA6390, controller does not lost packets but
* sequence number field of packat sometimes has error
* sequence number field of packet sometimes has error
* bits, so skip this checking for missing packet.
*/
while ((seq_no > qca_memdump->current_seq_no + 1) &&
@ -1571,6 +1571,20 @@ static void qca_cmd_timeout(struct hci_dev *hdev)
mutex_unlock(&qca->hci_memdump_lock);
}
static bool qca_prevent_wake(struct hci_dev *hdev)
{
struct hci_uart *hu = hci_get_drvdata(hdev);
bool wakeup;
/* UART driver handles the interrupt from BT SoC.So we need to use
* device handle of UART driver to get the status of device may wakeup.
*/
wakeup = device_may_wakeup(hu->serdev->ctrl->dev.parent);
bt_dev_dbg(hu->hdev, "wakeup status : %d", wakeup);
return !wakeup;
}
static int qca_wcn3990_init(struct hci_uart *hu)
{
struct qca_serdev *qcadev;
@ -1721,6 +1735,7 @@ static int qca_setup(struct hci_uart *hu)
qca_debugfs_init(hdev);
hu->hdev->hw_error = qca_hw_error;
hu->hdev->cmd_timeout = qca_cmd_timeout;
hu->hdev->prevent_wake = qca_prevent_wake;
} else if (ret == -ENOENT) {
/* No patch/nvm-config found, run with original fw/config */
set_bit(QCA_ROM_FW, &qca->flags);

401
drivers/bluetooth/virtio_bt.c Normal file
View File

@ -0,0 +1,401 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/skbuff.h>
#include <uapi/linux/virtio_ids.h>
#include <uapi/linux/virtio_bt.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
#define VERSION "0.1"
enum {
VIRTBT_VQ_TX,
VIRTBT_VQ_RX,
VIRTBT_NUM_VQS,
};
struct virtio_bluetooth {
struct virtio_device *vdev;
struct virtqueue *vqs[VIRTBT_NUM_VQS];
struct work_struct rx;
struct hci_dev *hdev;
};
static int virtbt_add_inbuf(struct virtio_bluetooth *vbt)
{
struct virtqueue *vq = vbt->vqs[VIRTBT_VQ_RX];
struct scatterlist sg[1];
struct sk_buff *skb;
int err;
skb = alloc_skb(1000, GFP_KERNEL);
sg_init_one(sg, skb->data, 1000);
err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL);
if (err < 0) {
kfree_skb(skb);
return err;
}
return 0;
}
static int virtbt_open(struct hci_dev *hdev)
{
struct virtio_bluetooth *vbt = hci_get_drvdata(hdev);
if (virtbt_add_inbuf(vbt) < 0)
return -EIO;
virtqueue_kick(vbt->vqs[VIRTBT_VQ_RX]);
return 0;
}
static int virtbt_close(struct hci_dev *hdev)
{
struct virtio_bluetooth *vbt = hci_get_drvdata(hdev);
int i;
cancel_work_sync(&vbt->rx);
for (i = 0; i < ARRAY_SIZE(vbt->vqs); i++) {
struct virtqueue *vq = vbt->vqs[i];
struct sk_buff *skb;
while ((skb = virtqueue_detach_unused_buf(vq)))
kfree_skb(skb);
}
return 0;
}
static int virtbt_flush(struct hci_dev *hdev)
{
return 0;
}
static int virtbt_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
{
struct virtio_bluetooth *vbt = hci_get_drvdata(hdev);
struct scatterlist sg[1];
int err;
memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
sg_init_one(sg, skb->data, skb->len);
err = virtqueue_add_outbuf(vbt->vqs[VIRTBT_VQ_TX], sg, 1, skb,
GFP_KERNEL);
if (err) {
kfree_skb(skb);
return err;
}
virtqueue_kick(vbt->vqs[VIRTBT_VQ_TX]);
return 0;
}
static int virtbt_setup_zephyr(struct hci_dev *hdev)
{
struct sk_buff *skb;
/* Read Build Information */
skb = __hci_cmd_sync(hdev, 0xfc08, 0, NULL, HCI_INIT_TIMEOUT);
if (IS_ERR(skb))
return PTR_ERR(skb);
bt_dev_info(hdev, "%s", (char *)(skb->data + 1));
hci_set_fw_info(hdev, "%s", skb->data + 1);
kfree_skb(skb);
return 0;
}
static int virtbt_set_bdaddr_zephyr(struct hci_dev *hdev,
const bdaddr_t *bdaddr)
{
struct sk_buff *skb;
/* Write BD_ADDR */
skb = __hci_cmd_sync(hdev, 0xfc06, 6, bdaddr, HCI_INIT_TIMEOUT);
if (IS_ERR(skb))
return PTR_ERR(skb);
kfree_skb(skb);
return 0;
}
static int virtbt_setup_intel(struct hci_dev *hdev)
{
struct sk_buff *skb;
/* Intel Read Version */
skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_CMD_TIMEOUT);
if (IS_ERR(skb))
return PTR_ERR(skb);
kfree_skb(skb);
return 0;
}
static int virtbt_set_bdaddr_intel(struct hci_dev *hdev, const bdaddr_t *bdaddr)
{
struct sk_buff *skb;
/* Intel Write BD Address */
skb = __hci_cmd_sync(hdev, 0xfc31, 6, bdaddr, HCI_INIT_TIMEOUT);
if (IS_ERR(skb))
return PTR_ERR(skb);
kfree_skb(skb);
return 0;
}
static int virtbt_setup_realtek(struct hci_dev *hdev)
{
struct sk_buff *skb;
/* Read ROM Version */
skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT);
if (IS_ERR(skb))
return PTR_ERR(skb);
bt_dev_info(hdev, "ROM version %u", *((__u8 *) (skb->data + 1)));
kfree_skb(skb);
return 0;
}
static int virtbt_shutdown_generic(struct hci_dev *hdev)
{
struct sk_buff *skb;
/* Reset */
skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
if (IS_ERR(skb))
return PTR_ERR(skb);
kfree_skb(skb);
return 0;
}
static void virtbt_rx_handle(struct virtio_bluetooth *vbt, struct sk_buff *skb)
{
__u8 pkt_type;
pkt_type = *((__u8 *) skb->data);
skb_pull(skb, 1);
switch (pkt_type) {
case HCI_EVENT_PKT:
case HCI_ACLDATA_PKT:
case HCI_SCODATA_PKT:
case HCI_ISODATA_PKT:
hci_skb_pkt_type(skb) = pkt_type;
hci_recv_frame(vbt->hdev, skb);
break;
}
}
static void virtbt_rx_work(struct work_struct *work)
{
struct virtio_bluetooth *vbt = container_of(work,
struct virtio_bluetooth, rx);
struct sk_buff *skb;
unsigned int len;
skb = virtqueue_get_buf(vbt->vqs[VIRTBT_VQ_RX], &len);
if (!skb)
return;
skb->len = len;
virtbt_rx_handle(vbt, skb);
if (virtbt_add_inbuf(vbt) < 0)
return;
virtqueue_kick(vbt->vqs[VIRTBT_VQ_RX]);
}
static void virtbt_tx_done(struct virtqueue *vq)
{
struct sk_buff *skb;
unsigned int len;
while ((skb = virtqueue_get_buf(vq, &len)))
kfree_skb(skb);
}
static void virtbt_rx_done(struct virtqueue *vq)
{
struct virtio_bluetooth *vbt = vq->vdev->priv;
schedule_work(&vbt->rx);
}
static int virtbt_probe(struct virtio_device *vdev)
{
vq_callback_t *callbacks[VIRTBT_NUM_VQS] = {
[VIRTBT_VQ_TX] = virtbt_tx_done,
[VIRTBT_VQ_RX] = virtbt_rx_done,
};
const char *names[VIRTBT_NUM_VQS] = {
[VIRTBT_VQ_TX] = "tx",
[VIRTBT_VQ_RX] = "rx",
};
struct virtio_bluetooth *vbt;
struct hci_dev *hdev;
int err;
__u8 type;
if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
return -ENODEV;
type = virtio_cread8(vdev, offsetof(struct virtio_bt_config, type));
switch (type) {
case VIRTIO_BT_CONFIG_TYPE_PRIMARY:
case VIRTIO_BT_CONFIG_TYPE_AMP:
break;
default:
return -EINVAL;
}
vbt = kzalloc(sizeof(*vbt), GFP_KERNEL);
if (!vbt)
return -ENOMEM;
vdev->priv = vbt;
vbt->vdev = vdev;
INIT_WORK(&vbt->rx, virtbt_rx_work);
err = virtio_find_vqs(vdev, VIRTBT_NUM_VQS, vbt->vqs, callbacks,
names, NULL);
if (err)
return err;
hdev = hci_alloc_dev();
if (!hdev) {
err = -ENOMEM;
goto failed;
}
vbt->hdev = hdev;
hdev->bus = HCI_VIRTIO;
hdev->dev_type = type;
hci_set_drvdata(hdev, vbt);
hdev->open = virtbt_open;
hdev->close = virtbt_close;
hdev->flush = virtbt_flush;
hdev->send = virtbt_send_frame;
if (virtio_has_feature(vdev, VIRTIO_BT_F_VND_HCI)) {
__u16 vendor;
virtio_cread(vdev, struct virtio_bt_config, vendor, &vendor);
switch (vendor) {
case VIRTIO_BT_CONFIG_VENDOR_ZEPHYR:
hdev->manufacturer = 1521;
hdev->setup = virtbt_setup_zephyr;
hdev->shutdown = virtbt_shutdown_generic;
hdev->set_bdaddr = virtbt_set_bdaddr_zephyr;
break;
case VIRTIO_BT_CONFIG_VENDOR_INTEL:
hdev->manufacturer = 2;
hdev->setup = virtbt_setup_intel;
hdev->shutdown = virtbt_shutdown_generic;
hdev->set_bdaddr = virtbt_set_bdaddr_intel;
set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
break;
case VIRTIO_BT_CONFIG_VENDOR_REALTEK:
hdev->manufacturer = 93;
hdev->setup = virtbt_setup_realtek;
hdev->shutdown = virtbt_shutdown_generic;
set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
break;
}
}
if (virtio_has_feature(vdev, VIRTIO_BT_F_MSFT_EXT)) {
__u16 msft_opcode;
virtio_cread(vdev, struct virtio_bt_config,
msft_opcode, &msft_opcode);
hci_set_msft_opcode(hdev, msft_opcode);
}
if (virtio_has_feature(vdev, VIRTIO_BT_F_AOSP_EXT))
hci_set_aosp_capable(hdev);
if (hci_register_dev(hdev) < 0) {
hci_free_dev(hdev);
err = -EBUSY;
goto failed;
}
return 0;
failed:
vdev->config->del_vqs(vdev);
return err;
}
static void virtbt_remove(struct virtio_device *vdev)
{
struct virtio_bluetooth *vbt = vdev->priv;
struct hci_dev *hdev = vbt->hdev;
hci_unregister_dev(hdev);
vdev->config->reset(vdev);
hci_free_dev(hdev);
vbt->hdev = NULL;
vdev->config->del_vqs(vdev);
kfree(vbt);
}
static struct virtio_device_id virtbt_table[] = {
{ VIRTIO_ID_BT, VIRTIO_DEV_ANY_ID },
{ 0 },
};
MODULE_DEVICE_TABLE(virtio, virtbt_table);
static const unsigned int virtbt_features[] = {
VIRTIO_BT_F_VND_HCI,
VIRTIO_BT_F_MSFT_EXT,
VIRTIO_BT_F_AOSP_EXT,
};
static struct virtio_driver virtbt_driver = {
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.feature_table = virtbt_features,
.feature_table_size = ARRAY_SIZE(virtbt_features),
.id_table = virtbt_table,
.probe = virtbt_probe,
.remove = virtbt_remove,
};
module_virtio_driver(virtbt_driver);
MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
MODULE_DESCRIPTION("Generic Bluetooth VIRTIO driver ver " VERSION);
MODULE_VERSION(VERSION);
MODULE_LICENSE("GPL");

2
drivers/infiniband/hw/mlx5/fs.c
View File

@ -879,7 +879,7 @@ static void mlx5_ib_set_rule_source_port(struct mlx5_ib_dev *dev,
misc_parameters_2);
MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
mlx5_eswitch_get_vport_metadata_for_match(esw,
mlx5_eswitch_get_vport_metadata_for_match(rep->esw,
rep->vport));
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
misc_parameters_2);

5
drivers/infiniband/hw/mlx5/ib_rep.c
View File

@ -20,7 +20,7 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
rep->rep_data[REP_IB].priv = ibdev;
write_lock(&ibdev->port[vport_index].roce.netdev_lock);
ibdev->port[vport_index].roce.netdev =
mlx5_ib_get_rep_netdev(dev->priv.eswitch, rep->vport);
mlx5_ib_get_rep_netdev(rep->esw, rep->vport);
write_unlock(&ibdev->port[vport_index].roce.netdev_lock);
return 0;
@ -123,8 +123,7 @@ struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
rep = dev->port[port - 1].rep;
return mlx5_eswitch_add_send_to_vport_rule(esw, rep->vport,
sq->base.mqp.qpn);
return mlx5_eswitch_add_send_to_vport_rule(esw, rep, sq->base.mqp.qpn);
}
static int mlx5r_rep_probe(struct auxiliary_device *adev,

3
drivers/infiniband/hw/mlx5/main.c
View File

@ -126,7 +126,6 @@ static struct mlx5_roce *mlx5_get_rep_roce(struct mlx5_ib_dev *dev,
struct net_device *ndev,
u8 *port_num)
{
struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
struct net_device *rep_ndev;
struct mlx5_ib_port *port;
int i;
@ -137,7 +136,7 @@ static struct mlx5_roce *mlx5_get_rep_roce(struct mlx5_ib_dev *dev,
continue;
read_lock(&port->roce.netdev_lock);
rep_ndev = mlx5_ib_get_rep_netdev(esw,
rep_ndev = mlx5_ib_get_rep_netdev(port->rep->esw,
port->rep->vport);
if (rep_ndev == ndev) {
read_unlock(&port->roce.netdev_lock);

9
drivers/isdn/hardware/mISDN/hfcmulti.c
View File

@ -173,13 +173,13 @@
#define MAX_FRAGS (32 * MAX_CARDS)
static LIST_HEAD(HFClist);
static spinlock_t HFClock; /* global hfc list lock */
static DEFINE_SPINLOCK(HFClock); /* global hfc list lock */
static void ph_state_change(struct dchannel *);
static struct hfc_multi *syncmaster;
static int plxsd_master; /* if we have a master card (yet) */
static spinlock_t plx_lock; /* may not acquire other lock inside */
static DEFINE_SPINLOCK(plx_lock); /* may not acquire other lock inside */
#define TYP_E1 1
#define TYP_4S 4
@ -2748,8 +2748,6 @@ hfcmulti_interrupt(int intno, void *dev_id)
if (hc->ctype != HFC_TYPE_E1)
ph_state_irq(hc, r_irq_statech);
}
if (status & V_EXT_IRQSTA)
; /* external IRQ */
if (status & V_LOST_STA) {
/* LOST IRQ */
HFC_outb(hc, R_INC_RES_FIFO, V_RES_LOST); /* clear irq! */
@ -5482,9 +5480,6 @@ HFCmulti_init(void)
printk(KERN_DEBUG "%s: IRQ_DEBUG IS ENABLED!\n", __func__);
#endif
spin_lock_init(&HFClock);
spin_lock_init(&plx_lock);
if (debug & DEBUG_HFCMULTI_INIT)
printk(KERN_DEBUG "%s: init entered\n", __func__);

14
drivers/isdn/hardware/mISDN/iohelper.h
View File

@ -13,14 +13,14 @@
#ifndef _IOHELPER_H
#define _IOHELPER_H
typedef u8 (read_reg_func)(void *hwp, u8 offset);
typedef void (write_reg_func)(void *hwp, u8 offset, u8 value);
typedef void (fifo_func)(void *hwp, u8 offset, u8 *datap, int size);
typedef u8 (read_reg_func)(void *hwp, u8 offset);
typedef void (write_reg_func)(void *hwp, u8 offset, u8 value);
typedef void (fifo_func)(void *hwp, u8 offset, u8 *datap, int size);
struct _ioport {
u32 port;
u32 ale;
};
struct _ioport {
u32 port;
u32 ale;
};
#define IOFUNC_IO(name, hws, ap) \
static u8 Read##name##_IO(void *p, u8 off) { \

13
drivers/isdn/mISDN/dsp_core.c
View File

@ -176,9 +176,9 @@ MODULE_LICENSE("GPL");
/*int spinnest = 0;*/
spinlock_t dsp_lock; /* global dsp lock */
struct list_head dsp_ilist;
struct list_head conf_ilist;
DEFINE_SPINLOCK(dsp_lock); /* global dsp lock */
LIST_HEAD(dsp_ilist);
LIST_HEAD(conf_ilist);
int dsp_debug;
int dsp_options;
int dsp_poll, dsp_tics;
@ -953,7 +953,6 @@ dsp_ctrl(struct mISDNchannel *ch, u_int cmd, void *arg)
{
struct dsp *dsp = container_of(ch, struct dsp, ch);
u_long flags;
int err = 0;
if (debug & DEBUG_DSP_CTRL)
printk(KERN_DEBUG "%s:(%x)\n", __func__, cmd);
@ -998,7 +997,7 @@ dsp_ctrl(struct mISDNchannel *ch, u_int cmd, void *arg)
module_put(THIS_MODULE);
break;
}
return err;
return 0;
}
static void
@ -1170,10 +1169,6 @@ static int __init dsp_init(void)
printk(KERN_INFO "mISDN_dsp: DSP clocks every %d samples. This equals "
"%d jiffies.\n", dsp_poll, dsp_tics);
spin_lock_init(&dsp_lock);
INIT_LIST_HEAD(&dsp_ilist);
INIT_LIST_HEAD(&conf_ilist);
/* init conversion tables */
dsp_audio_generate_law_tables();
dsp_silence = (dsp_options & DSP_OPT_ULAW) ? 0xff : 0x2a;

9
drivers/isdn/mISDN/l1oip_core.c
View File

@ -200,7 +200,7 @@
The complete socket opening and closing is done by a thread.
When the thread opened a socket, the hc->socket descriptor is set. Whenever a
packet shall be sent to the socket, the hc->socket must be checked wheter not
packet shall be sent to the socket, the hc->socket must be checked whether not
NULL. To prevent change in socket descriptor, the hc->socket_lock must be used.
To change the socket, a recall of l1oip_socket_open() will safely kill the
socket process and create a new one.
@ -229,8 +229,8 @@
static const char *l1oip_revision = "2.00";
static int l1oip_cnt;
static spinlock_t l1oip_lock;
static struct list_head l1oip_ilist;
static DEFINE_SPINLOCK(l1oip_lock);
static LIST_HEAD(l1oip_ilist);
#define MAX_CARDS 16
static u_int type[MAX_CARDS];
@ -1440,9 +1440,6 @@ l1oip_init(void)
printk(KERN_INFO "mISDN: Layer-1-over-IP driver Rev. %s\n",
l1oip_revision);
INIT_LIST_HEAD(&l1oip_ilist);
spin_lock_init(&l1oip_lock);
if (l1oip_4bit_alloc(ulaw))
return -ENOMEM;

3
drivers/net/Kconfig
View File

@ -502,6 +502,8 @@ source "drivers/net/wan/Kconfig"
source "drivers/net/ieee802154/Kconfig"
source "drivers/net/wwan/Kconfig"
config XEN_NETDEV_FRONTEND
tristate "Xen network device frontend driver"
depends on XEN
@ -579,6 +581,7 @@ config NETDEVSIM
depends on DEBUG_FS
depends on INET
depends on IPV6 || IPV6=n
depends on PSAMPLE || PSAMPLE=n
select NET_DEVLINK
help
This driver is a developer testing tool and software model that can

3
drivers/net/Makefile
View File

@ -45,7 +45,7 @@ obj-$(CONFIG_ARCNET) += arcnet/
obj-$(CONFIG_DEV_APPLETALK) += appletalk/
obj-$(CONFIG_CAIF) += caif/
obj-$(CONFIG_CAN) += can/
obj-y += dsa/
obj-$(CONFIG_NET_DSA) += dsa/
obj-$(CONFIG_ETHERNET) += ethernet/
obj-$(CONFIG_FDDI) += fddi/
obj-$(CONFIG_HIPPI) += hippi/
@ -68,6 +68,7 @@ obj-$(CONFIG_SUNGEM_PHY) += sungem_phy.o
obj-$(CONFIG_WAN) += wan/
obj-$(CONFIG_WLAN) += wireless/
obj-$(CONFIG_IEEE802154) += ieee802154/
obj-$(CONFIG_WWAN) += wwan/
obj-$(CONFIG_VMXNET3) += vmxnet3/
obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o

3
drivers/net/Space.c
View File

@ -59,9 +59,6 @@ static int __init probe_list2(int unit, struct devprobe2 *p, int autoprobe)
* look for EISA/PCI cards in addition to ISA cards).
*/
static struct devprobe2 isa_probes[] __initdata = {
#if defined(CONFIG_HP100) && defined(CONFIG_ISA) /* ISA, EISA */
{hp100_probe, 0},
#endif
#ifdef CONFIG_3C515
{tc515_probe, 0},
#endif

1
drivers/net/bareudp.c
View File

@ -218,6 +218,7 @@ static struct socket *bareudp_create_sock(struct net *net, __be16 port)
if (err < 0)
return ERR_PTR(err);
udp_allow_gso(sock->sk);
return sock;
}

2
drivers/net/bonding/bond_alb.c
View File

@ -1098,7 +1098,7 @@ static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1,
* If @slave's permanent hw address is different both from its current
* address and from @bond's address, then somewhere in the bond there's
* a slave that has @slave's permanet address as its current address.
* We'll make sure that that slave no longer uses @slave's permanent address.
* We'll make sure that slave no longer uses @slave's permanent address.
*
* Caller must hold RTNL and no other locks
*/

9
drivers/net/bonding/bond_main.c
View File

@ -964,7 +964,7 @@ static bool bond_should_notify_peers(struct bonding *bond)
}
/**
* change_active_interface - change the active slave into the specified one
* bond_change_active_slave - change the active slave into the specified one
* @bond: our bonding struct
* @new_active: the new slave to make the active one
*
@ -4391,9 +4391,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
int agg_id = 0;
int ret = 0;
#ifdef CONFIG_LOCKDEP
WARN_ON(lockdep_is_held(&bond->mode_lock));
#endif
might_sleep();
usable_slaves = kzalloc(struct_size(usable_slaves, arr,
bond->slave_cnt), GFP_KERNEL);
@ -4406,7 +4404,9 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
struct ad_info ad_info;
spin_lock_bh(&bond->mode_lock);
if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
spin_unlock_bh(&bond->mode_lock);
pr_debug("bond_3ad_get_active_agg_info failed\n");
/* No active aggragator means it's not safe to use
* the previous array.
@ -4414,6 +4414,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
bond_reset_slave_arr(bond);
goto out;
}
spin_unlock_bh(&bond->mode_lock);
agg_id = ad_info.aggregator_id;
}
bond_for_each_slave(bond, slave, iter) {

9
drivers/net/bonding/bond_options.c
View File

@ -640,6 +640,15 @@ static void bond_opt_error_interpret(struct bonding *bond,
netdev_err(bond->dev, "option %s: unable to set because the bond device is up\n",
opt->name);
break;
case -ENODEV:
if (val && val->string) {
p = strchr(val->string, '\n');
if (p)
*p = '\0';
netdev_err(bond->dev, "option %s: interface %s does not exist!\n",
opt->name, val->string);
}
break;
default:
break;
}

2
drivers/net/can/Kconfig
View File

@ -103,7 +103,7 @@ config CAN_FLEXCAN
config CAN_GRCAN
tristate "Aeroflex Gaisler GRCAN and GRHCAN CAN devices"
depends on OF && HAS_DMA
depends on OF && HAS_DMA && HAS_IOMEM
help
Say Y here if you want to use Aeroflex Gaisler GRCAN or GRHCAN.
Note that the driver supports little endian, even though little

153
drivers/net/can/c_can/c_can.c
View File

@ -132,7 +132,6 @@
/* For the high buffers we clear the interrupt bit and newdat */
#define IF_COMM_RCV_HIGH (IF_COMM_RCV_LOW | IF_COMM_CLR_NEWDAT)
/* Receive setup of message objects */
#define IF_COMM_RCV_SETUP (IF_COMM_MASK | IF_COMM_ARB | IF_COMM_CONTROL)
@ -161,9 +160,7 @@
#define IF_MCONT_TX (IF_MCONT_TXIE | IF_MCONT_EOB)
/*
* Use IF1 for RX and IF2 for TX
*/
/* Use IF1 for RX and IF2 for TX */
#define IF_RX 0
#define IF_TX 1
@ -173,9 +170,6 @@
/* Wait for ~1 sec for INIT bit */
#define INIT_WAIT_MS 1000
/* napi related */
#define C_CAN_NAPI_WEIGHT C_CAN_MSG_OBJ_RX_NUM
/* c_can lec values */
enum c_can_lec_type {
LEC_NO_ERROR = 0,
@ -189,8 +183,7 @@ enum c_can_lec_type {
LEC_MASK = LEC_UNUSED,
};
/*
* c_can error types:
/* c_can error types:
* Bus errors (BUS_OFF, ERROR_WARNING, ERROR_PASSIVE) are supported
*/
enum c_can_bus_error_types {
@ -253,7 +246,6 @@ static void c_can_obj_update(struct net_device *dev, int iface, u32 cmd, u32 obj
udelay(1);
}
netdev_err(dev, "Updating object timed out\n");
}
static inline void c_can_object_get(struct net_device *dev, int iface,
@ -268,8 +260,7 @@ static inline void c_can_object_put(struct net_device *dev, int iface,
c_can_obj_update(dev, iface, cmd | IF_COMM_WR, obj);
}
/*
* Note: According to documentation clearing TXIE while MSGVAL is set
/* Note: According to documentation clearing TXIE while MSGVAL is set
* is not allowed, but works nicely on C/DCAN. And that lowers the I/O
* load significantly.
*/
@ -285,8 +276,7 @@ static void c_can_inval_msg_object(struct net_device *dev, int iface, int obj)
{
struct c_can_priv *priv = netdev_priv(dev);
priv->write_reg(priv, C_CAN_IFACE(ARB1_REG, iface), 0);
priv->write_reg(priv, C_CAN_IFACE(ARB2_REG, iface), 0);
priv->write_reg32(priv, C_CAN_IFACE(ARB1_REG, iface), 0);
c_can_inval_tx_object(dev, iface, obj);
}
@ -309,12 +299,11 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
if (!rtr)
arb |= IF_ARB_TRANSMIT;
/*
* If we change the DIR bit, we need to invalidate the buffer
/* If we change the DIR bit, we need to invalidate the buffer
* first, i.e. clear the MSGVAL flag in the arbiter.
*/
if (rtr != (bool)test_bit(idx, &priv->tx_dir)) {
u32 obj = idx + C_CAN_MSG_OBJ_TX_FIRST;
u32 obj = idx + priv->msg_obj_tx_first;
c_can_inval_msg_object(dev, iface, obj);
change_bit(idx, &priv->tx_dir);
@ -447,18 +436,16 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
if (can_dropped_invalid_skb(dev, skb))
return NETDEV_TX_OK;
/*
* This is not a FIFO. C/D_CAN sends out the buffers
/* This is not a FIFO. C/D_CAN sends out the buffers
* prioritized. The lowest buffer number wins.
*/
idx = fls(atomic_read(&priv->tx_active));
obj = idx + C_CAN_MSG_OBJ_TX_FIRST;
obj = idx + priv->msg_obj_tx_first;
/* If this is the last buffer, stop the xmit queue */
if (idx == C_CAN_MSG_OBJ_TX_NUM - 1)
if (idx == priv->msg_obj_tx_num - 1)
netif_stop_queue(dev);
/*
* Store the message in the interface so we can call
/* Store the message in the interface so we can call
* can_put_echo_skb(). We must do this before we enable
* transmit as we might race against do_tx().
*/
@ -467,7 +454,7 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
can_put_echo_skb(skb, dev, idx, 0);
/* Update the active bits */
atomic_add((1 << idx), &priv->tx_active);
atomic_add(BIT(idx), &priv->tx_active);
/* Start transmission */
c_can_object_put(dev, IF_TX, obj, IF_COMM_TX);
@ -511,7 +498,7 @@ static int c_can_set_bittiming(struct net_device *dev)
reg_brpe = brpe & BRP_EXT_BRPE_MASK;
netdev_info(dev,
"setting BTR=%04x BRPE=%04x\n", reg_btr, reg_brpe);
"setting BTR=%04x BRPE=%04x\n", reg_btr, reg_brpe);
ctrl_save = priv->read_reg(priv, C_CAN_CTRL_REG);
ctrl_save &= ~CONTROL_INIT;
@ -527,8 +514,7 @@ static int c_can_set_bittiming(struct net_device *dev)
return c_can_wait_for_ctrl_init(dev, priv, 0);
}
/*
* Configure C_CAN message objects for Tx and Rx purposes:
/* Configure C_CAN message objects for Tx and Rx purposes:
* C_CAN provides a total of 32 message objects that can be configured
* either for Tx or Rx purposes. Here the first 16 message objects are used as
* a reception FIFO. The end of reception FIFO is signified by the EoB bit
@ -538,17 +524,18 @@ static int c_can_set_bittiming(struct net_device *dev)
*/
static void c_can_configure_msg_objects(struct net_device *dev)
{
struct c_can_priv *priv = netdev_priv(dev);
int i;
/* first invalidate all message objects */
for (i = C_CAN_MSG_OBJ_RX_FIRST; i <= C_CAN_NO_OF_OBJECTS; i++)
for (i = priv->msg_obj_rx_first; i <= priv->msg_obj_num; i++)
c_can_inval_msg_object(dev, IF_RX, i);
/* setup receive message objects */
for (i = C_CAN_MSG_OBJ_RX_FIRST; i < C_CAN_MSG_OBJ_RX_LAST; i++)
for (i = priv->msg_obj_rx_first; i < priv->msg_obj_rx_last; i++)
c_can_setup_receive_object(dev, IF_RX, i, 0, 0, IF_MCONT_RCV);
c_can_setup_receive_object(dev, IF_RX, C_CAN_MSG_OBJ_RX_LAST, 0, 0,
c_can_setup_receive_object(dev, IF_RX, priv->msg_obj_rx_last, 0, 0,
IF_MCONT_RCV_EOB);
}
@ -572,8 +559,7 @@ static int c_can_software_reset(struct net_device *dev)
return 0;
}
/*
* Configure C_CAN chip:
/* Configure C_CAN chip:
* - enable/disable auto-retransmission
* - set operating mode
* - configure message objects
@ -714,12 +700,21 @@ static void c_can_do_tx(struct net_device *dev)
struct net_device_stats *stats = &dev->stats;
u32 idx, obj, pkts = 0, bytes = 0, pend, clr;
clr = pend = priv->read_reg(priv, C_CAN_INTPND2_REG);
if (priv->msg_obj_tx_last > 32)
pend = priv->read_reg32(priv, C_CAN_INTPND3_REG);
else
pend = priv->read_reg(priv, C_CAN_INTPND2_REG);
clr = pend;
while ((idx = ffs(pend))) {
idx--;
pend &= ~(1 << idx);
obj = idx + C_CAN_MSG_OBJ_TX_FIRST;
pend &= ~BIT(idx);
obj = idx + priv->msg_obj_tx_first;
/* We use IF_RX interface instead of IF_TX because we
* are called from c_can_poll(), which runs inside
* NAPI. We are not trasmitting.
*/
c_can_inval_tx_object(dev, IF_RX, obj);
can_get_echo_skb(dev, idx, NULL);
bytes += priv->dlc[idx];
@ -729,7 +724,7 @@ static void c_can_do_tx(struct net_device *dev)
/* Clear the bits in the tx_active mask */
atomic_sub(clr, &priv->tx_active);
if (clr & (1 << (C_CAN_MSG_OBJ_TX_NUM - 1)))
if (clr & BIT(priv->msg_obj_tx_num - 1))
netif_wake_queue(dev);
if (pkts) {
@ -739,20 +734,18 @@ static void c_can_do_tx(struct net_device *dev)
}
}
/*
* If we have a gap in the pending bits, that means we either
/* If we have a gap in the pending bits, that means we either
* raced with the hardware or failed to readout all upper
* objects in the last run due to quota limit.
*/
static u32 c_can_adjust_pending(u32 pend)
static u32 c_can_adjust_pending(u32 pend, u32 rx_mask)
{
u32 weight, lasts;
if (pend == RECEIVE_OBJECT_BITS)
if (pend == rx_mask)
return pend;
/*
* If the last set bit is larger than the number of pending
/* If the last set bit is larger than the number of pending
* bits we have a gap.
*/
weight = hweight32(pend);
@ -762,19 +755,19 @@ static u32 c_can_adjust_pending(u32 pend)
if (lasts == weight)
return pend;
/*
* Find the first set bit after the gap. We walk backwards
/* Find the first set bit after the gap. We walk backwards
* from the last set bit.
*/
for (lasts--; pend & (1 << (lasts - 1)); lasts--);
for (lasts--; pend & BIT(lasts - 1); lasts--)
;
return pend & ~((1 << lasts) - 1);
return pend & ~GENMASK(lasts - 1, 0);
}
static inline void c_can_rx_object_get(struct net_device *dev,
struct c_can_priv *priv, u32 obj)
{
c_can_object_get(dev, IF_RX, obj, priv->comm_rcv_high);
c_can_object_get(dev, IF_RX, obj, priv->comm_rcv_high);
}
static inline void c_can_rx_finalize(struct net_device *dev,
@ -803,8 +796,7 @@ static int c_can_read_objects(struct net_device *dev, struct c_can_priv *priv,
continue;
}
/*
* This really should not happen, but this covers some
/* This really should not happen, but this covers some
* odd HW behaviour. Do not remove that unless you
* want to brick your machine.
*/
@ -825,19 +817,22 @@ static int c_can_read_objects(struct net_device *dev, struct c_can_priv *priv,
static inline u32 c_can_get_pending(struct c_can_priv *priv)
{
u32 pend = priv->read_reg(priv, C_CAN_NEWDAT1_REG);
u32 pend;
if (priv->msg_obj_rx_last > 16)
pend = priv->read_reg32(priv, C_CAN_NEWDAT1_REG);
else
pend = priv->read_reg(priv, C_CAN_NEWDAT1_REG);
return pend;
}
/*
* theory of operation:
/* theory of operation:
*
* c_can core saves a received CAN message into the first free message
* object it finds free (starting with the lowest). Bits NEWDAT and
* INTPND are set for this message object indicating that a new message
* has arrived. To work-around this issue, we keep two groups of message
* objects whose partitioning is defined by C_CAN_MSG_OBJ_RX_SPLIT.
* has arrived.
*
* We clear the newdat bit right away.
*
@ -848,23 +843,16 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota)
struct c_can_priv *priv = netdev_priv(dev);
u32 pkts = 0, pend = 0, toread, n;
/*
* It is faster to read only one 16bit register. This is only possible
* for a maximum number of 16 objects.
*/
BUILD_BUG_ON_MSG(C_CAN_MSG_OBJ_RX_LAST > 16,
"Implementation does not support more message objects than 16");
while (quota > 0) {
if (!pend) {
pend = c_can_get_pending(priv);
if (!pend)
break;
/*
* If the pending field has a gap, handle the
/* If the pending field has a gap, handle the
* bits above the gap first.
*/
toread = c_can_adjust_pending(pend);
toread = c_can_adjust_pending(pend,
priv->msg_obj_rx_mask);
} else {
toread = pend;
}
@ -883,7 +871,7 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota)
}
static int c_can_handle_state_change(struct net_device *dev,
enum c_can_bus_error_types error_type)
enum c_can_bus_error_types error_type)
{
unsigned int reg_err_counter;
unsigned int rx_err_passive;
@ -979,8 +967,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
struct can_frame *cf;
struct sk_buff *skb;
/*
* early exit if no lec update or no error.
/* early exit if no lec update or no error.
* no lec update means that no CAN bus event has been detected
* since CPU wrote 0x7 value to status reg.
*/
@ -999,8 +986,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
if (unlikely(!skb))
return 0;
/*
* check for 'last error code' which tells us the
/* check for 'last error code' which tells us the
* type of the last error to occur on the CAN bus
*/
cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
@ -1049,7 +1035,8 @@ static int c_can_poll(struct napi_struct *napi, int quota)
/* Only read the status register if a status interrupt was pending */
if (atomic_xchg(&priv->sie_pending, 0)) {
priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG);
priv->last_status = priv->read_reg(priv, C_CAN_STS_REG);
curr = priv->last_status;
/* Ack status on C_CAN. D_CAN is self clearing */
if (priv->type != BOSCH_D_CAN)
priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED);
@ -1147,7 +1134,7 @@ static int c_can_open(struct net_device *dev)
/* register interrupt handler */
err = request_irq(dev->irq, &c_can_isr, IRQF_SHARED, dev->name,
dev);
dev);
if (err < 0) {
netdev_err(dev, "failed to request interrupt\n");
goto exit_irq_fail;
@ -1195,17 +1182,31 @@ static int c_can_close(struct net_device *dev)
return 0;
}
struct net_device *alloc_c_can_dev(void)
struct net_device *alloc_c_can_dev(int msg_obj_num)
{
struct net_device *dev;
struct c_can_priv *priv;
int msg_obj_tx_num = msg_obj_num / 2;
dev = alloc_candev(sizeof(struct c_can_priv), C_CAN_MSG_OBJ_TX_NUM);
dev = alloc_candev(struct_size(priv, dlc, msg_obj_tx_num),
msg_obj_tx_num);
if (!dev)
return NULL;
priv = netdev_priv(dev);
netif_napi_add(dev, &priv->napi, c_can_poll, C_CAN_NAPI_WEIGHT);
priv->msg_obj_num = msg_obj_num;
priv->msg_obj_rx_num = msg_obj_num - msg_obj_tx_num;
priv->msg_obj_rx_first = 1;
priv->msg_obj_rx_last =
priv->msg_obj_rx_first + priv->msg_obj_rx_num - 1;
priv->msg_obj_rx_mask = GENMASK(priv->msg_obj_rx_num - 1, 0);
priv->msg_obj_tx_num = msg_obj_tx_num;
priv->msg_obj_tx_first = priv->msg_obj_rx_last + 1;
priv->msg_obj_tx_last =
priv->msg_obj_tx_first + priv->msg_obj_tx_num - 1;
netif_napi_add(dev, &priv->napi, c_can_poll, priv->msg_obj_rx_num);
priv->dev = dev;
priv->can.bittiming_const = &c_can_bittiming_const;
@ -1239,7 +1240,7 @@ int c_can_power_down(struct net_device *dev)
/* Wait for the PDA bit to get set */
time_out = jiffies + msecs_to_jiffies(INIT_WAIT_MS);
while (!(priv->read_reg(priv, C_CAN_STS_REG) & STATUS_PDA) &&
time_after(time_out, jiffies))
time_after(time_out, jiffies))
cpu_relax();
if (time_after(jiffies, time_out))
@ -1280,7 +1281,7 @@ int c_can_power_up(struct net_device *dev)
/* Wait for the PDA bit to get clear */
time_out = jiffies + msecs_to_jiffies(INIT_WAIT_MS);
while ((priv->read_reg(priv, C_CAN_STS_REG) & STATUS_PDA) &&
time_after(time_out, jiffies))
time_after(time_out, jiffies))
cpu_relax();
if (time_after(jiffies, time_out)) {

43
drivers/net/can/c_can/c_can.h
View File

@ -22,23 +22,6 @@
#ifndef C_CAN_H
#define C_CAN_H
/* message object split */
#define C_CAN_NO_OF_OBJECTS 32
#define C_CAN_MSG_OBJ_RX_NUM 16
#define C_CAN_MSG_OBJ_TX_NUM 16
#define C_CAN_MSG_OBJ_RX_FIRST 1
#define C_CAN_MSG_OBJ_RX_LAST (C_CAN_MSG_OBJ_RX_FIRST + \
C_CAN_MSG_OBJ_RX_NUM - 1)
#define C_CAN_MSG_OBJ_TX_FIRST (C_CAN_MSG_OBJ_RX_LAST + 1)
#define C_CAN_MSG_OBJ_TX_LAST (C_CAN_MSG_OBJ_TX_FIRST + \
C_CAN_MSG_OBJ_TX_NUM - 1)
#define C_CAN_MSG_OBJ_RX_SPLIT 9
#define C_CAN_MSG_RX_LOW_LAST (C_CAN_MSG_OBJ_RX_SPLIT - 1)
#define RECEIVE_OBJECT_BITS 0x0000ffff
enum reg {
C_CAN_CTRL_REG = 0,
C_CAN_CTRL_EX_REG,
@ -76,6 +59,7 @@ enum reg {
C_CAN_NEWDAT2_REG,
C_CAN_INTPND1_REG,
C_CAN_INTPND2_REG,
C_CAN_INTPND3_REG,
C_CAN_MSGVAL1_REG,
C_CAN_MSGVAL2_REG,
C_CAN_FUNCTION_REG,
@ -137,6 +121,7 @@ static const u16 __maybe_unused reg_map_d_can[] = {
[C_CAN_NEWDAT2_REG] = 0x9E,
[C_CAN_INTPND1_REG] = 0xB0,
[C_CAN_INTPND2_REG] = 0xB2,
[C_CAN_INTPND3_REG] = 0xB4,
[C_CAN_MSGVAL1_REG] = 0xC4,
[C_CAN_MSGVAL2_REG] = 0xC6,
[C_CAN_IF1_COMREQ_REG] = 0x100,
@ -164,7 +149,6 @@ static const u16 __maybe_unused reg_map_d_can[] = {
};
enum c_can_dev_id {
BOSCH_C_CAN_PLATFORM,
BOSCH_C_CAN,
BOSCH_D_CAN,
};
@ -176,6 +160,7 @@ struct raminit_bits {
struct c_can_driver_data {
enum c_can_dev_id id;
unsigned int msg_obj_num;
/* RAMINIT register description. Optional. */
const struct raminit_bits *raminit_bits; /* Array of START/DONE bit positions */
@ -197,26 +182,34 @@ struct c_can_priv {
struct napi_struct napi;
struct net_device *dev;
struct device *device;
unsigned int msg_obj_num;
unsigned int msg_obj_rx_num;
unsigned int msg_obj_tx_num;
unsigned int msg_obj_rx_first;
unsigned int msg_obj_rx_last;
unsigned int msg_obj_tx_first;
unsigned int msg_obj_tx_last;
u32 msg_obj_rx_mask;
atomic_t tx_active;
atomic_t sie_pending;
unsigned long tx_dir;
int last_status;
u16 (*read_reg) (const struct c_can_priv *priv, enum reg index);
void (*write_reg) (const struct c_can_priv *priv, enum reg index, u16 val);
u32 (*read_reg32) (const struct c_can_priv *priv, enum reg index);
void (*write_reg32) (const struct c_can_priv *priv, enum reg index, u32 val);
u16 (*read_reg)(const struct c_can_priv *priv, enum reg index);
void (*write_reg)(const struct c_can_priv *priv, enum reg index, u16 val);
u32 (*read_reg32)(const struct c_can_priv *priv, enum reg index);
void (*write_reg32)(const struct c_can_priv *priv, enum reg index, u32 val);
void __iomem *base;
const u16 *regs;
void *priv; /* for board-specific data */
enum c_can_dev_id type;
struct c_can_raminit raminit_sys; /* RAMINIT via syscon regmap */
void (*raminit) (const struct c_can_priv *priv, bool enable);
void (*raminit)(const struct c_can_priv *priv, bool enable);
u32 comm_rcv_high;
u32 rxmasked;
u32 dlc[C_CAN_MSG_OBJ_TX_NUM];
u32 dlc[];
};
struct net_device *alloc_c_can_dev(void);
struct net_device *alloc_c_can_dev(int msg_obj_num);
void free_c_can_dev(struct net_device *dev);
int register_c_can_dev(struct net_device *dev);
void unregister_c_can_dev(struct net_device *dev);

31
drivers/net/can/c_can/c_can_pci.c
View File

@ -31,6 +31,8 @@ enum c_can_pci_reg_align {
struct c_can_pci_data {
/* Specify if is C_CAN or D_CAN */
enum c_can_dev_id type;
/* Number of message objects */
unsigned int msg_obj_num;
/* Set the register alignment in the memory */
enum c_can_pci_reg_align reg_align;
/* Set the frequency */
@ -41,32 +43,31 @@ struct c_can_pci_data {
void (*init)(const struct c_can_priv *priv, bool enable);
};
/*
* 16-bit c_can registers can be arranged differently in the memory
/* 16-bit c_can registers can be arranged differently in the memory
* architecture of different implementations. For example: 16-bit
* registers can be aligned to a 16-bit boundary or 32-bit boundary etc.
* Handle the same by providing a common read/write interface.
*/
static u16 c_can_pci_read_reg_aligned_to_16bit(const struct c_can_priv *priv,
enum reg index)
enum reg index)
{
return readw(priv->base + priv->regs[index]);
}
static void c_can_pci_write_reg_aligned_to_16bit(const struct c_can_priv *priv,
enum reg index, u16 val)
enum reg index, u16 val)
{
writew(val, priv->base + priv->regs[index]);
}
static u16 c_can_pci_read_reg_aligned_to_32bit(const struct c_can_priv *priv,
enum reg index)
enum reg index)
{
return readw(priv->base + 2 * priv->regs[index]);
}
static void c_can_pci_write_reg_aligned_to_32bit(const struct c_can_priv *priv,
enum reg index, u16 val)
enum reg index, u16 val)
{
writew(val, priv->base + 2 * priv->regs[index]);
}
@ -88,13 +89,13 @@ static u32 c_can_pci_read_reg32(const struct c_can_priv *priv, enum reg index)
u32 val;
val = priv->read_reg(priv, index);
val |= ((u32) priv->read_reg(priv, index + 1)) << 16;
val |= ((u32)priv->read_reg(priv, index + 1)) << 16;
return val;
}
static void c_can_pci_write_reg32(const struct c_can_priv *priv, enum reg index,
u32 val)
u32 val)
{
priv->write_reg(priv, index + 1, val >> 16);
priv->write_reg(priv, index, val);
@ -142,14 +143,13 @@ static int c_can_pci_probe(struct pci_dev *pdev,
pci_resource_len(pdev, c_can_pci_data->bar));
if (!addr) {
dev_err(&pdev->dev,
"device has no PCI memory resources, "
"failing adapter\n");
"device has no PCI memory resources, failing adapter\n");
ret = -ENOMEM;
goto out_release_regions;
}
/* allocate the c_can device */
dev = alloc_c_can_dev();
dev = alloc_c_can_dev(c_can_pci_data->msg_obj_num);
if (!dev) {
ret = -ENOMEM;
goto out_iounmap;
@ -217,7 +217,7 @@ static int c_can_pci_probe(struct pci_dev *pdev,
}
dev_dbg(&pdev->dev, "%s device registered (regs=%p, irq=%d)\n",
KBUILD_MODNAME, priv->regs, dev->irq);
KBUILD_MODNAME, priv->regs, dev->irq);
return 0;
@ -252,8 +252,9 @@ static void c_can_pci_remove(struct pci_dev *pdev)
pci_disable_device(pdev);
}
static const struct c_can_pci_data c_can_sta2x11= {
static const struct c_can_pci_data c_can_sta2x11 = {
.type = BOSCH_C_CAN,
.msg_obj_num = 32,
.reg_align = C_CAN_REG_ALIGN_32,
.freq = 52000000, /* 52 Mhz */
.bar = 0,
@ -261,6 +262,7 @@ static const struct c_can_pci_data c_can_sta2x11= {
static const struct c_can_pci_data c_can_pch = {
.type = BOSCH_C_CAN,
.msg_obj_num = 32,
.reg_align = C_CAN_REG_32,
.freq = 50000000, /* 50 MHz */
.init = c_can_pci_reset_pch,
@ -269,7 +271,7 @@ static const struct c_can_pci_data c_can_pch = {
#define C_CAN_ID(_vend, _dev, _driverdata) { \
PCI_DEVICE(_vend, _dev), \
.driver_data = (unsigned long)&_driverdata, \
.driver_data = (unsigned long)&(_driverdata), \
}
static const struct pci_device_id c_can_pci_tbl[] = {
@ -279,6 +281,7 @@ static const struct pci_device_id c_can_pci_tbl[] = {
c_can_pch),
{},
};
static struct pci_driver c_can_pci_driver = {
.name = KBUILD_MODNAME,
.id_table = c_can_pci_tbl,

Some files were not shown because too many files have changed in this diff Show More